Showing papers on "Object detection published in 1986"
01 Apr 1986
TL;DR: A processor based on systolic arrays is described that realizes the object detection algorithm developed in the paper and also examines a computational structure tailored to one of the algorithms.
Abstract: In this paper, two-dimensional stochastic linear models are used in developing algorithms for image analysis such as classification, segmentation, and object detection in images characterized by textured backgrounds. These models generate two-dimensional random processes as outputs to which statistical inference procedures can naturally be applied. A common thread throughout our algorithms is the interpretation of the inference procedures in terms of linear prediction residuals. This interpretation leads to statistical tests more insightful than the original tests and makes the procedures computationally tractable. This paper also examines a computational structure tailored to one of the algorithms. In particular, we describe a processor based on systolic arrays that realizes the object detection algorithm developed in the paper.
110 citations
07 Apr 1986
TL;DR: Techniques for outdoor scene analysis using range data are described to build a 3-D representation of the environment of an mobile robot equipped with a range sensor and have been successfully applied to the problem of path planning through obstacles.
Abstract: This paper describes techniques for outdoor scene analysis using range data. The purpose of these techniques is to build a 3-D representation of the environment of an mobile robot equipped with a range sensor. Algorithms are presented for scene segmentation, object detection, map building, and object recognition. We present results obtained in an outdoor navigation environment in which a laser range finder is mounted on a vehicle. These results have been successfully applied to the problem of path planning through obstacles.
105 citations
TL;DR: The limits of adaptive quantization to reduce intrinsic noise are presented, and it is shown that a signal processing approach is especially convenient to measure the performances of a detector based on the Hough transform.
Abstract: Exact predictions of the performances of the Hough detection of straight lines in two-dimensional images are presented for rectangular and circular retinas, in Cartesian and normal parameterization, in the case of noisy signals. Detection of circles, under the same assumptions, is discussed. The limits of adaptive quantization to reduce intrinsic noise are presented, and it is shown that a signal processing approach is especially convenient to measure the performances of a detector based on the Hough transform.
68 citations
07 Apr 1986
TL;DR: An algorithm based on velocity and distance bounds is described which is both useful and complete in terms of collision detection and is contrasted with existing collision detection methods.
Abstract: The collision detection problem is encountered whenever objects are to be manipulated in the real world. Efficient solutions to this problem must intelligently decide when in time and where in space to check for interference among the objects. Complete solutions must guarantee that no collision can be overlooked. Useful solutions should also report the precise space/time points at which colliding objects begin and end contact. An algorithm based on velocity and distance bounds is described which is both useful and complete. Experiments are presented which measure the efficiency of the algorithm on a variety of test cases. The algorithm is contrasted with existing collision detection methods.
63 citations
09 Jun 1986
TL;DR: The Adaptive Least Squares Correlation (ALSC) as mentioned in this paper is a general and flexible technique for many different image matching problems, which allows simultaneous local geometrical image shaping and radiometric corrections, whereby the system parameters are automatically assessed, corrected and thus optimized with respect to the specific signal during the least squares iterations.
Abstract: The Adaptive Least Squares Correlation is a general and flexible technique for many different image matching problems. It allows for simultaneous local geometrical image shaping and radiometric corrections, whereby the system parameters are automatically assessed, corrected and thus optimized with respect to the specific signal during the least squares iterations. Precision and reliability measures can be developed to assess the quality of the match. A stabilization and improvement of the correlation procedure can be achieved through the simultaneous consideration of object point intersection conditions from conjugate rays and other sensor and object constraints. These geometrical constraints limit the search area size, reduce the number of alternatives, increase the precision and reliability of matching and provide simultaneously 3D-point positioning information. The method can be applied to correlation, object detection and measurement, and image tracking, while the 3D-information provided can be readily utilized for tasks requiring inspection, manipulation, object tracking and navigation. As an exciting new prospect the method can be applied to more than two images at a time. This paper outlines the basic concept of the technique.
41 citations
01 Oct 1986
TL;DR: Cellular arrays can realize very efficiently pointwise or local operations on images, thanks to their mesh organization, but these structures lack of efficient and flexible global data extraction mechanism to perform higher level tasks such as feature extraction, object detection, and so on.
Abstract: Because of the large volume of data handled during image analysis, a high degree of parallel processing is required in special purpose image processing computers. Cellular arrays, as, for example, CLIP4 [Duff 76], MPP [Batcher 80], DAP [Flanders 77] can realize very efficiently pointwise or local operations on images, thanks to their mesh organization, but these structures lack of efficient and flexible global data extraction mechanism to perform higher level tasks such as feature extraction, object detection, and so on….
24 citations
TL;DR: Stereoscopic motion is an approach for comparing image change due to motion in a stereo pair of image sequences that predicts where the object point will pass with respect to the camera system.
Abstract: Stereoscopic motion is an approach for comparing image change due to motion in a stereo pair of image sequences. Qualitatively, the relative image change shows that an object point is approaching, receding, or remaining at constant depth. Quantitatively, the relative change predicts where the object point will pass with respect to the camera system.
24 citations
TL;DR: A real-time range measurement device for detecting the range, shape, and position of a three-dimensional object by a light stripe projection method that can discriminate three types of machine parts on a conveyor belt in 4.0 s.
Abstract: This correspondence describes a real-time range measurement device for detecting the range, shape, and position of a three-dimensional object by a light stripe projection method. The device consists of a light stripe projection unit, a light stripe scanning control unit, a TV camera, a signal processing unit, and a microcomputer. While a laser light stripe is projected and scanned on an object at a high speed, range measurements and their calculations are done with special hardware. Range data are obtained by triangulation. This device can detect the range and shape of the object placed in a 60 cm square area at a distance of 100 cm in 490 ms by 48 × 50 points. The measurement accuracy of the device is ±2.0 cm. A sorting system for machine parts using this device has also been developed. By use of a unique range gating method, the system can discriminate three types of machine parts on a conveyor belt in 4.0 s.
23 citations
01 Jan 1986
TL;DR: 3-D reference object models are established as a decision tree, and recognition of unknown objects is accomplished through measuring and comparing input object features hierarchically with these of the reference objects associated with the decision tree.
Abstract: The objective of this paper is to develop an object recognitlon system through the combination of 2-D tactile image array and visual sensors. A video camera is used to acquire a top view image of an object and two tactile sensing arrays mounted on a gripper are used to detect the tactile information about the lateral surfaces of the object. 3-D reference object models are established as a decision tree, and recognition of unknown objects is accomplished through measuring and comparing input object features hierarchically with these of the reference objects associated with the decision tree. The clustering process and recognition procedures are described. The recognition scheme has been implemented. The resulting decision tree is also presented.
22 citations
07 Apr 1986
TL;DR: A contour based motion estimation technique is presented applied to the measurement of the optic-flow field from image sequences, which has proved to be very robust in real scene analysis and an acceptable time for computation is required.
Abstract: In this paper a contour based motion estimation technique is presented applied to the measurement of the optic-flow field from image sequences. In particular two experimental situations are considered: the former, in which a fixed camera analyzes a scene with some moving objects in order to detect their trajectories; the latter, in which a sensor moves in a static environment, determining the depth map of the "world". For the first case, we compute for every contour the prevalent direction of movement. For the second, we solve the problem of recovering the 3D structure of the worldby computing the depth field from a sequence of images acquired during a motion of the camera, controlled in order to mantain the fixation point (i.e. the point projected over the image plane) still during the entire sequence. The algorithm has proved to be very robust in real scene analysis and an acceptable time for computation is required. Some experimental results are presented.
21 citations
TL;DR: A computationally efficient algorithm for object detection from a segmented image using a binary relation called region adjacency and the analysis of algebraic structure of regions is given.
01 Apr 1986
TL;DR: A vision system using range image for the industrial application, where simple basic surface primitives are considered and are extracted from the range image to form smallest distinctive feature sets (SDFS) to form the object model.
Abstract: Our goal is to develop a vision system using range image for the industrial application. In the system, simple basic surface primitives are considered and are extracted from the range image. From the robust geometric features contained in the primitives, rotation-invariant characteristics are then extracted to form smallest distinctive feature sets (SDFS). The set of SDFSs and the relationships between elements in SDFS and the kernel are stored to form the object model. The recognition process involves first extracting a set of SDFSs from the image and matching the extracted SDFSs with the stored SDFSs. If the kernels determined for SDFSs matched are consistent, object can be detected and its location and orientation in the viewer-centered coordinate system (VCC) can be determined.
Patent•
27 Mar 1986
TL;DR: In this article, a retroreflector is fitted in the region of the object and can be used to maintain a considerable luminous efficiency from the light rays reflected into the endoscope.
Abstract: The invention relates to an optical arrangement for object detection, in which the optical examination is performed with an endoscope (EK). In order to be able to carry out reliably even examinations of objects (OB) having completely or partially lustrous surfaces, a retroreflector (RR) is fitted in the region of the object (OB) and can be used to maintain a considerable luminous efficiency from the light rays reflected into the endoscope (EK). The invention can be used in particular in the automated testing of moulded parts.
Patent•
09 May 1986
TL;DR: In this article, the modulation frequency of a modulation light or a light projection-reception cycle is made free to set to prevent interference between object detection sensors, which enables one sensor to extract the modulation waveform for others from the waveform of the light received even when receiving modulation lights mixed from the light emitting elements 1 of a plurality of object detectors thereby preventing the interference between the sensors.
Abstract: PURPOSE:To detect a plurality of object detection sensors used from effect due to interference, by making the modulation frequency of a modulation light or a light projection-reception cycle thereof free to set to prevent interference between object detection sensors. CONSTITUTION:An optical system is made up of a light receiving element 2 which directly receives light projected from a light emitting element 1 and a light receiving element 3 which receives reflected light from an object. Then, a signal processing section 6 includes an interference preventing means comprising a frequency setting means 13 which controls an oscillator 4 to set the modulation frequency for modulating the light projected as desired by the light emitting element 1 and a filter 11 which only extracts the modulation frequency peculiar to itself from the output of light receiving elements 2 and 3 to be inputted into an object recognizing means 12. The modulation frequency of the modulation light or the projection/reception cycle thereof is made free to set. This enables one sensor to extract the modulation waveform for others from the waveform of the light received even when receiving modulation lights mixed from the light emitting elements 1 of a plurality of object detection sensors thereby preventing the interference between the sensors.
01 Dec 1986
TL;DR: The efficacy of applying recently developed models for visual edge detection, in particular, the Marr-Hildreth Laplacian-of-a-Gaussian operator to the problem of automatically detecting sustained intensity changes, corresponding to object boundaries, in SAR imagery is analyzed.
Abstract: We consider the problem of automatically detecting sustained intensity changes, corresponding to object boundaries, in SAR imagery. The problem is complicated by the speckle noise found in SAR imagery, which is highly correlated and signal-dependent. In this paper, we analyze the efficacy of applying to this problem recently developed models for visual edge detection, in particular, the Marr-Hildreth Laplacian-of-a-Gaussian operator.
Patent•
13 Jun 1986
TL;DR: In this paper, an ultrasonic receiver which receives a reflected ultrasonic pulse signal between plural ultrasonic transmitter-receivers and adjacent ultrasonic receivers is used to shorten the necessary time of scanning and to increase the response speed of body detection.
Abstract: PURPOSE:To shorten the necessary time of scanning and to increase the response speed of body detection by providing an ultrasonic receiver which receives an ultrasonic pulse signal between plural ultrasonic transmitter-receivers and adjacent transmitter-receivers, and scanning the operations of the transmitter- receivers. CONSTITUTION:When the 1st ultrasonic transmitter-receiver A sends an ultrasonic pulse signal, the transmitter-receiver A and the 1st ultrasonic receiver B' receive reflected pulses and their total detection area is the detection area S1 consisting of individual areas (a) and (b'). The total detection area of the 2nd ultrasonic transmitter-receiver C and the 2nd ultrasonic receiver D' is the detection area S2 consisting of individual detection areas (c) and (d'), and the individual detection area of the 3rd ultrasonic wave transmitter-receiver E is (e). Then, a scanning means scan the operations of the 1st - the 3rd ultrasonic transmitter-receivers A, C, and E successively and repeatedly to perform detection covering all object detection areas. Thus, the detection area is extended and the response speed is increased.
10 Dec 1986
TL;DR: The workstation is comprised of two complementary, high-performance processors connected via a high-speed interface: the Pixar 2D Image computer and the Symbolics 36xx Lisp machine.
Abstract: This paper describes a workstation and a software development environment designed to facilitate the investigation of integrated signal/symbol processing in image understanding and graphics processing. The workstation is comprised of two complementary, high-performance processors connected via a high-speed interface: the Pixar 2D Image computer and the Symbolics 36xx Lisp machine. Some of the current and potential applications of the system include developing and evaluating new image analysis and feature extraction algorithms, investigating the role of the extracted features in perceptual aggregation, object detection/identification and scene analysis, and assisting in the creation of prototypical image understanding systems.
01 Jan 1986
TL;DR: In object detection, exactness of position is not usually the case (but there are exceptions)—the primary purpose being that of detecting the presence or absence of an object.
Abstract: As pointed out in an earlier article on “Position, Motion, Speed, Velocity,” position is central among the geometric variables. Generally1, in position control and motion systems, control action is taken to establish a position or series of positions that lie along a trajectory or path. In these cases the exact coordinates of position are usually paramount. In object detection, exactness of position is not usually the case (but there are exceptions)—the primary purpose being that of detecting the presence or absence of an object.