Showing papers on "Object detection published in 2000"

A Bayesian computer vision system for modeling human interactions

Abstract: We describe a real-time computer vision and machine learning system for modeling and recognizing human behaviors in a visual surveillance task. The system deals in particularly with detecting when interactions between people occur and classifying the type of interaction. Examples of interesting interaction behaviors include following another person, altering one's path to meet another, and so forth. Our system combines top-down with bottom-up information in a closed feedback loop, with both components employing a statistical Bayesian approach. We propose and compare two different state-based learning architectures, namely, HMMs and CHMMs for modeling behaviors and interactions. Finally, a synthetic "Alife-style" training system is used to develop flexible prior models for recognizing human interactions. We demonstrate the ability to use these a priori models to accurately classify real human behaviors and interactions with no additional tuning or training.

A Trainable System for Object Detection

Abstract: This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in terms of an overcomplete dictionary of local, oriented, multiscale intensity differences between adjacent regions, efficiently computable as a Haar wavelet transform. This example-based learning approach implicitly derives a model of an object class by training a support vector machine classifier using a large set of positive and negative examples. We present results on face, people, and car detection tasks using the same architecture. In addition, we quantify how the representation affects detection performance by considering several alternate representations including pixels and principal components. We also describe a real-time application of our person detection system as part of a driver assistance system.

A statistical method for 3D object detection applied to faces and cars

Abstract: In this paper, we describe a statistical method for 3D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithm that can reliably detect passenger cars over a wide range of viewpoints.

Pedestrian Detection from a Moving Vehicle

Abstract: This paper presents a prototype system for pedestrian detection on-board a moving vehicle The system uses a generic two-step approach for efficient object detection In the first step, contour features are used in a hierarchical template matching approach to efficiently "lock" onto candidate solutions Shape matching is based on Distance Transforms By capturing the objects shape variability by means of a template hierarchy and using a combined coarse-to-fine approach in shape and parameter space, this method achieves very large speed-ups compared to a brute-force method We have measured gains of several orders of magnitude The second step utilizes the richer set of intensity features in a pattern classification approach to verify the candidate solutions (ie using Radial Basis Functions) We present experimental results on pedestrian detection off-line and on-board our Urban Traffic Assistant vehicle and discuss the challenges that lie ahead

Introduction to the special section on video surveillance

Abstract: UTOMATED video surveillance addresses real-time observation of people and vehicles within a busy environment, leading to a description of their actions and interactions. The technical issues include moving object detection and tracking, object classification, human motion analysis, and activity understanding, touching on many of the core topics of computer vision, pattern analysis, and aritificial intelligence. Video surveillance has spawned large research projects in the United States, Europe, and Japan, and has been the topic of several international conferences and workshops in recent years. There are immediate needs for automated surveillance systems in commercial, law enforcement, and military applications. Mounting video cameras is cheap, but finding available human resources to observe the output is expensive. Although surveillance cameras are already prevalent in banks, stores, and parking lots, video data currently is used only “after the fact” as a forensic tool, thus losing its primary benefit as an active, real-time medium. What is needed is continuous 24-hour monitoring of surveillance video to alert security officers to a burglary in progress or to a suspicious individual loitering in the parking lot, while there is still time to prevent the crime. In addition to the obvious security applications, video surveillance technology has been proposed to measure traffic flow, detect accidents on highways, monitor pedestrian congestion in public spaces, compile consumer demographics in shopping malls and amusement parks, log routine maintainence tasks at nuclear facilities, and count endangered species. The numerous military applications include patrolling national borders, measuring the flow of refugees in troubled areas, monitoring peace treaties, and providing secure perimeters around bases and embassies. The 11 papers in this special section illustrate topics and techniques at the forefront of video surveillance research. These papers can be loosely organized into three categories. Detection and tracking involves real-time extraction of moving objects from video and continuous tracking over time to form persistent object trajectories. C. Stauffer and W.E.L. Grimson introduce unsupervised statistical learning techniques to cluster object trajectories produced by adaptive background subtraction into descriptions of normal scene activity. Viewpoint-specific trajectory descriptions from multiple cameras are combined into a common scene coordinate system using a calibration technique described by L. Lee, R. Romano, and G. Stein, who automatically determine the relative exterior orientation of overlapping camera views by observing a sparse set of moving objects on flat terrain. Two papers address the accumulation of noisy motion evidence over time. R. Pless, T. Brodský, and Y. Aloimonos detect and track small objects in aerial video sequences by first compensating for the self-motion of the aircraft, then accumulating residual normal flow to acquire evidence of independent object motion. L. Wixson notes that motion in the image does not always signify purposeful travel by an independently moving object (examples of such “motion clutter” are wind-blown tree branches and sun reflections off rippling water) and devises a flow-based salience measure to highlight objects that tend to move in a consistent direction over time. Human motion analysis is concerned with detecting periodic motion signifying a human gait and acquiring descriptions of human body pose over time. R. Cutler and L.S. Davis plot an object’s self-similarity across all pairs of frames to form distinctive patterns that classify bipedal, quadripedal, and rigid object motion. Y. Ricquebourg and P. Bouthemy track apparent contours in XT slices of an XYT sequence volume to robustly delineate and track articulated human body structure. I. Haritaoglu, D. Harwood, and L.S. Davis present W4, a surveillance system specialized to the task of looking at people. The W4 system can locate people and segment their body parts, build simple appearance models for tracking, disambiguate between and separately track multiple individuals in a group, and detect carried objects such as boxes and backpacks. Activity analysis deals with parsing temporal sequences of object observations to produce high-level descriptions of agent actions and multiagent interactions. In our opinion, this will be the most important area of future research in video surveillance. N.M. Oliver, B. Rosario, and A.P. Pentland introduce Coupled Hidden Markov Models (CHMMs) to detect and classify interactions consisting of two interleaved agent action streams and present a training method based on synthetic agents to address the problem of parameter estimation from limited real-world training examples. M. Brand and V. Kettnaker present an entropyminimization approach to estimating HMM topology and

Stereo- and neural network-based pedestrian detection

Abstract: Pedestrian detection is essential to avoid dangerous traffic situations. We present a fast and robust algorithm for detecting pedestrians in a cluttered scene from a pair of moving cameras. This is achieved through stereo-based segmentation and neural network-based recognition. The algorithm includes three steps. First, we segment the image into sub-image object candidates using disparities discontinuity. Second, we merge and split the sub-image object candidates into sub-images that satisfy pedestrian size and shape constraints. Third, we use intensity gradients of the candidate sub-images as input to a trained neural network for pedestrian recognition. The experiments on a large number of urban street scenes demonstrate that the proposed algorithm: (1) can detect pedestrians in various poses, shapes, sizes, clothing, and occlusion status; (2) runs in real-time; and (3) is robust to illumination and background changes.

Constrained subpixel target detection for remotely sensed imagery

Abstract: Target detection in remotely sensed images can be conducted spatially, spectrally or both. The difficulty of detecting targets in remotely sensed images with spatial image analysis arises from the fact that the ground sampling distance is generally larger than the size of targets of interest in which case targets are embedded in a single pixel and cannot be detected spatially. Under this circumstance target detection must be carried out at subpixel level and spectral analysis offers a valuable alternative. In this paper, the problem of subpixel spectral detection of targets in remote sensing images is considered, where two constrained target detection approaches are studied and compared. One is a target abundance-constrained approach, referred to as nonnegatively constrained least squares (NCLS) method. It is a constrained least squares spectral mixture analysis method which implements a nonnegativity constraint on the abundance fractions of targets of interest. Another is a target signature-constrained approach, called constrained energy minimization (CEM) method. It constrains the desired target signature with a specific gain while minimizing effects caused by other unknown signatures. A quantitative study is conducted to analyze the advantages and disadvantages of both methods. Some suggestions are further proposed to mitigate their disadvantages.

Methods and apparatus for stationary object detection

Abstract: The present invention provides systems and methods for measuring the likelihood that detected stationary objects are not normally present at a sensed location. Such systems and methods may be used by other systems to which information from the present invention are communicated, for minimizing nuisance alerts in onboard object detection systems such as collision warning, collision avoidance, and/or adaptive cruise control systems. The system includes at least one vehicle mounted sensor capable of sensing at least a target object and providing data related to the target object. The system also comprises a locating device which is capable of determining and providing data related to the location of the machine or vehicle and a processing unit which receives the data from the sensor and the data from the locating device. The processing unit is configured to determine a probability estimate or measure of likelihood that the target object is not a normally present object based upon a comparison to previously recorded data from a reference storage device. The reference storage device stores the previously recorded data acquired from at least one similar sensor and a vehicle locating device while operating in the same geographic area, or stores data derived from such previously recorded data. The invention may enhance vehicle collision warning, collision avoidance and/or adaptive cruise control systems as examples.

A statistical approach to 3d object detection applied to faces and cars

Abstract: In this thesis, we describe a statistical method for 3D object detection. In this method, we decompose the 3D geometry of each object into a small number of viewpoints. For each viewpoint, we construct a decision rule that determines if the object is present at that specific orientation. Each decision rule uses the statistics of both object appearance and “non-object” visual appearance. We represent each set of statistics using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints.

Towards automatic discovery of object categories

Abstract: We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (features). The variability within a class is represented by a join probability density function on the shape of the constellation and the appearance of the parts. Our method automatically identifies distinctive features in the training set. The set of model parameters is then learned using expectation maximization. When trained on different, unlabeled and unsegmented views of a class of objects, each component of the mixture model can adapt to represent a subset of the views. Similarly, different component models can also "specialize" on sub-classes of an object class. Experiments on images of human heads, leaves from different species of trees, and motor-cars demonstrate that the method works well over a wide variety of objects.

Moving shadow and object detection in traffic scenes

Abstract: We present an algorithm for segmentation of traffic scenes that distinguishes moving objects from their moving cast shadows. A fading memory estimator calculates mean and variance of all three color components for each background pixel. Given the statistics for a background pixel, simple rules for calculating its statistics when covered by a shadow are used. Then, MAP classification decisions are made for each pixel. In addition to the color features, we examine the use of neighborhood information to produce smoother classification. We also propose the use of temporal information by modifying class a priori probabilities based on predictions from the previous frame.

Multi-modal interface apparatus and method

Abstract: In the multi-modal interface apparatus of the present invention, a gaze object detection section always detects a user's gaze object. The user inputs at least one medium of sound information, character information, image information and operation information through a media input section. In order to effectively input and output information between the user and the apparatus, a personified image presentation section presents a personified image to the user based on the user's gaze object. A control section controls a reception of the inputted media from the media input section based on the user's gaze object.

Walking pedestrian recognition

Abstract: In previous years, many methods providing the ability to recognize rigid obstacles-sedans and trucks-have been developed. These methods provide the driver with relevant information. They are able to cope reliably with scenarios on motorways. Nevertheless, not much attention has been given to image processing approaches to increase the safety of pedestrians in urban environments. In the paper, a method for the detection, tracking, and final recognition of pedestrians crossing the moving observer's trajectory is suggested. A combination of data- and model-driven approaches is realized. The initial detection process is based on a fusion of texture analysis, model-based grouping of, most likely, the geometric features of pedestrians, and inverse-perspective mapping (binocular vision). Additionally, motion patterns of limb movements are analyzed to determine initial object-hypotheses. The tracking of the quasirigid part of the body is performed by different algorithms that have been successfully employed for the tracking of sedans, trucks, motorbikes, and pedestrians. The final classification is obtained by a temporal analysis of the walking process.

Scene modeling for wide area surveillance and image synthesis

Abstract: We present a method for modeling a scene that is observed by a moving camera, where only a portion of the scene is visible at any time. This method uses mixture models to represent pixels in a panoramic view, and to construct a "background image" that contains only static (non-moving) parts of the scene. The method can be used to reliably detect moving objects in a video sequence, detect patterns of activity over a wide field of view, and remove moving objects from a video or panoramic mosaic. The method also yields improved results in detecting moving objects and in constructing mosaics in the presence of moving objects, when compared with techniques that are not based on scene modeling. We present examples illustrating the results.

Visual perception of obstacles and vehicles for platooning

Abstract: Presents the methods for sensing obstacles and vehicles implemented on the University of Parma experimental vehicle (ARGO). The ARGO project is briefly described along with its main objectives; the prototype vehicle and its functionalities are presented. The perception of the environment is performed through the processing of images acquired from the vehicle. Details about the stereo vision-based detection of generic obstacles are given, along with a measurement of the performance of the method; then a new approach for leading vehicles detection is described, relying on symmetry detection in monocular images. The paper concludes with a description of the current implementation of the control system, based on a gain scheduled controller, which allows the vehicle to follow the road or other vehicles.

Real-time video-shot detection for scene surveillance applications

Abstract: A surveillance system with automatic video-shot detection and indexing capabilities is presented. The proposed system aims at detecting the presence of abandoned objects in a guarded environment and at automatically performing online semantic video segmentation in order to facilitate the human operator's task of retrieving the cause of an alarm. The former task is performed by operating image segmentation based on temporal rank-order filtering, followed by classification in order to reduce false alarms. The latter task is performed by operating temporal video segmentation when an alarm is detected. In the clips of interest, the key frame is the one depicting a person leaving a dangerous object, and is determined on the basis of a feature indicating the movement around the dangerous region. Experimental results are reported in terms of static region detection, classification, clip and key-frame detection errors versus different levels of complexity of the guarded environment, in order to establish the performance that can be expected from the system in different situations.

Hyperspectral imagery: clutter adaptation in anomaly detection

Abstract: Hyperspectral sensors are passive sensors that simultaneously record images for hundreds of contiguous and narrowly spaced regions of the electromagnetic spectrum. Each image corresponds to the same ground scene, thus creating a cube of images that contain both spatial and spectral information about the objects and backgrounds in the scene. In this paper, we present an adaptive anomaly detector designed assuming that the background clutter in the hyperspectral imagery is a three-dimensional Gauss-Markov random field. This model leads to an efficient and effective algorithm for discriminating man-made objects (the anomalies) in real hyperspectral imagery. The major focus of the paper is on the adaptive stage of the detector, i.e., the estimation of the Gauss-Markov random field parameters. We develop three methods: maximum-likelihood; least squares; and approximate maximum-likelihood. We study these approaches along three directions: estimation error performance, computational cost, and detection performance. In terms of estimation error, we derive the Cramer-Rao bounds and carry out Monte Carlo simulation studies that show that the three estimation procedures have similar performance when the fields are highly correlated, as is often the case with real hyperspectral imagery. The approximate maximum-likelihood method has a clear advantage from the computational point of view. Finally, we test extensively with real hyperspectral imagery the adaptive anomaly detector incorporating either the least squares or the approximate maximum-likelihood estimators. Its performance compares very favorably with that of the RX algorithm.

Adaptive change detection for real-time surveillance applications

Abstract: This paper describes a new real-time approach for detecting changes in grey level image sequences, which were taken from stationary cameras. This new method combines a temporal difference method with an adaptive background model subtraction scheme. When changes in illumination occur the background model is automatically adapted to suit the new conditions. For the adaptation of the background model a new method is proposed, which avoids reinforcement of adaptation errors by performing the adaptation solely on those regions that were detected by the temporal difference method rather than using the regions resulting from the overall algorithm. Thus the adaptation process is separated from the results of its own background subtraction algorithm. The change detector was successfully tested both in a vision-based workspace monitoring system for different kinds of non-autonomous service robots and in a surveillance scenario, in which it was the task to detect people in a subway-platform scenario. The proposed real-time algorithm showed recognition rates of up to 90% in the foreground and 84% in the background and performed in all cases at least 12% better than the alternative method of adaptive background estimation which uses a modified Kalman filtering technique.

Hands free optical scanner trigger

Abstract: A method and apparatus for detecting an object within the field of view of an optical reader, such as a bar code scanner (102). Object detection is determined by a software algorithm that may be embedded in a controller (104) or microprocessor contained within the scanner. The object detection software algorithm uses a current trigger threshold to determine whether there is a change in the amount of reflected light energy (116) sufficient to indicate the presence of motion in the scanner (102) field of view. The system may normalize random noise within a scanner's circuitry and accommodate varying degrees of reflectivity of target materials, without requiring additional circuitry or reflective tape to accurately detect an object.

Illumination-invariant change detection

Abstract: Moving objects in image sequences acquired by a static camera can be detected by analyzing the grey-level difference between successive frames. Direct motion detection, however, will also detect fast variations of scene illumination. This paper describes a method for motion detection that is considerably less sensitive to time-varying illumination. It is based on combining a motion detection algorithm with an homomorphic filter which effectively suppresses variable scene illumination. To this end, the acquired image sequence is modelled as being generated by an illumination and a reflectance component that are approximately separated by the filter. Detection of changes in the reflectance component is directly related to scene changes, i.e., object motion. Real video data are used to illustrate the system's performance.

A semantic event-detection approach and its application to detecting hunts in wildlife video

Abstract: We propose a three-level video-event detection methodology and apply it to animal-hunt detection in wildlife documentaries. The first level extracts color, texture, and motion features, and detects shot boundaries and moving object blobs. The mid-level employs a neural network to determine the object class of the moving object blobs. This level also generates shot descriptors that combine features from the first level and inferences from the mid-level. The shot descriptors are then used by the domain-specific inference process at the third level to detect video segments that match the user defined event model. The proposed approach has been applied to the detection of hunts in wildlife documentaries. Our method can be applied to different events by adapting the classifier at the intermediate level and by specifying a new event model at the highest level. Event-based video indexing, summarization, and browsing are among the applications of the proposed approach.

A step towards sequence-to-sequence alignment

Abstract: The paper presents an approach for establishing correspondences in time and in space between two different video sequences of the same dynamic scene, recorded by stationary uncalibrated video cameras. The method simultaneously estimates both spatial alignment as well as temporal synchronization (temporal alignment) between the two sequences, using all available spatio-temporal information. Temporal variations between image frames (such as moving objects or changes in scene illumination) are powerful cues for alignment, which cannot be exploited by standard image-to-image alignment techniques. We show that by folding spatial and temporal cues into a single alignment framework, situations which are inherently ambiguous for traditional image-to-image alignment methods, are often uniquely resolved by sequence-to-sequence alignment. We also present a "direct" method for sequence-to-sequence alignment. The algorithm simultaneously estimates spatial and temporal alignment parameters directly from measurable sequence quantities, without requiring prior estimation of point correspondences, frame correspondences, or moving object detection. Results are shown on real image sequences taken by multiple video cameras.

Vision-guided automatic parking for smart car

Abstract: Presents our work on automatic parking of a smart car that relies on vision to estimate free parking slots. All problems involved in implementing an automatic parking behavior are discussed. Solutions are given together with experimental results obtained from real data.

Object Detection System

Abstract: An object detection system, in particular for a motor vehicle, has multiple object detectors and/or operating modes with which different detection ranges and/or detection zones are detected In this case, an object detector is preferably a radar sensor which has a relatively large detection range with a relatively small angular detection zone in a first operating mode and has a detection range that is small relative to the first with an enlarged angular detection zone in a second operating mode

Method to aid object detection in images by incorporating contextual information

Abstract: The invention uses fuzzy logic and/or probability distributions to automatically calculate and display the effects of contextual information on the confidence that an object in an image is an object of interest. The goal is to assist in determining the location and type of target objects of interest in that imagery. The imagery can come from any kind of imaging sensor or can be non-sensor imagery (e.g., two-and three-dimensional maps), and can be live or archived imagery. The locations of context objects can be provided by a human or a computer. The resulting set of data, including the original imagery, the locations of context objects, any results from AOD, and predictions about target object type and location, can be combined into a display that helps a human better understand where target object appears in the imagery.

Statistic and knowledge-based moving object detection in traffic scenes

Abstract: The most common approach used for vision-based traffic surveillance consists of a fast segmentation of moving visual objects (MVOs) in the scene together with an intelligent reasoning module capable of identifying, tracking and classifying the MVOs in dependency of the system goal. In this paper we describe our approach for MVOs segmentation in an unstructured traffic environment. We consider complex situations with moving people, vehicles and infrastructures that have different aspect model and motion model. In this case we define a specific approach based on background subtraction with statistic and knowledge-based background update. We show many results of real-time tracking of traffic MVOs in outdoor traffic scene such as roads, parking area intersections, and entrance with barriers.

Reconstruction of a scene with multiple linearly moving objects

Abstract: We describe an algorithm for reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the moving objects and the camera motion simultaneously. The number of the moving objects is automatically detected without prior motion segmentation. Assuming that the objects are moving linearly with constant speeds, we propose a unified geometrical representation of the static scene and the moving objects. This representation enables the embedding of the motion constraints into the scene structure, which leads to a factorization-based algorithm. Experimental results on synthetic and real images are presented.

A distributed surveillance system for detection of abandoned objects in unmanned railway environments

Abstract: In this paper, a distributed video-surveillance system for the detection of dangerous situations related to the presence of abandoned objects in the waiting rooms of unattended railway stations is presented. The image sequences, acquired with a monochromatic camera placed in each guarded room, are processed by a local PC-based image-processing system, devoted to detecting the presence of abandoned objects. When an abandoned object is recognized, an alarm issue is transmitted to a remote control center located a few miles from the guarded stations. A multimedia communication system based on direct sequence code-division multiple-access (DS/CDMA) techniques aims at ensuring secure and noise-robust wireless transmission links between the guarded stations and the remote control center where the processing results are displayed to the human operator. Results concern: 1) the performances of each local image processing system in terms of false-alarm and misdetection probabilities, and 2) the performances of the CDMA multimedia transmission system in terms of bit error rates (BERs) and quality of service (QoS).

Signal processing for object detection system

Abstract: Methods and apparatus for detecting objects. In one embodiment, a person entering a secured or “Safe Zone™” is illuminated with low-power polarized radio waves. Differently polarized waves which are reflected back from the person are collected and measured. In a preferred embodiment, concealed weapons are detected by calculating the difference of a pair of differences (Delta A and B) of different polarized reflected energy (upper and lower curves in the two graphs) in the time domain, and by using signal processing methods and apparatus to improve the reliability of the detection process.