Ichiro Masaki

Bio: Ichiro Masaki is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Image processing & Object detection. The author has an hindex of 22, co-authored 49 publications receiving 1523 citations. Previous affiliations of Ichiro Masaki include Honda.

A shape-independent method for pedestrian detection with far-infrared images

Abstract: Nighttime driving is more dangerous than daytime driving-particularly for senior drivers. Three to four times as many driving-related deaths occur at night than in the daytime. To improve the safety of night driving, automatic pedestrian detection based on infrared images has drawn increased attention because pedestrians tend to stand out more against the background in infrared images than they do in visible light images. Nevertheless, pedestrian detection in infrared images is by no means trivial-many of the known difficulties carry over from visible light images, such as image variability occasioned by pedestrians being in different poses. Typically, several different pedestrian templates have to be used in order to deal with a range of poses. Furthermore, pedestrian detection is difficult because of poor infrared image quality (low resolution, low contrast, few distinguishable feature points, little texture information, etc.) and misleading signals. To address these problems, this paper introduces a shape-independent pedestrian-detection method. Our segmentation algorithm first estimates pedestrians' horizontal locations through projection-based horizontal segmentation and then determines pedestrians' vertical locations through brightness/bodyline-based vertical segmentation. Our classification method defines multidimensional histogram-, inertia-, and contrast-based classification features. The features are shape-independent, complementary to one another, and capture the statistical similarities of image patches containing pedestrians with different poses. Thus, our pedestrian-detection system needs only one pedestrian template-corresponding to a generic walking pose-and avoids brute-force searching for pedestrians throughout whole images, which typically involves brightness-similarity comparisons between candidate image patches and a multiplicity of pedestrian templates. Our pedestrian-detection system is neither based on tracking nor does it depend on camera calibration to determine the relationship between an object's height and its vertical image locations. Thus, it is less restricted in applicability. Even if much work is still needed to bridge the gap between present pedestrian-detection performance and the high reliability required for real-world applications, our pedestrian-detection system is straightforward and provides encouraging results in improving speed, reliability, and simplicity.

Single-chip imager system with programmable dynamic range

Abstract: The imager system of the invention, provided in a semiconductor substrate, includes a plurality of photosensitive, charge integrating pixels that are arranged in rows and columns of a pixel array for capturing illumination of a scene to be imaged. Each pixel includes a photogenerated charge accumulation region of the semiconductor substrate and a sense node at which an electrical signal, indicative of pixel charge accumulation, can be measured without discharging the accumulation region. Pixel access control circuitry is connected to pixel array rows and columns to deliver pixel access signals generated by the access control circuitry for independently accessing a selected pixel in the array. An input interface circuit is connected to accept a dynamic range specification input for the array pixels. Integration control circuitry is connected to access a selected pixel of the array to read the sense node electrical signal of the selected pixel, and configured to generate pixel-specific integration control signals delivered to the selected pixel, independent of other pixels, based on dynamic range specification input provided by the input interface circuit. An output interface circuit is connected to the pixel array to produce output image data based on sense node electrical signals from the pixel array.

Preceding vehicle recognition based on learning from sample images

Abstract: Preceding vehicle recognition is an important enabling technology for developing a driver assistance system and an autonomous vehicle system. However, this is difficult for computer vision to achieve because of the variety of shapes and colors in which vehicles are made. In this paper, we propose a novel vision-based preceding vehicle recognition method, which has the capability of recognizing a wide selection of vehicles. In the proposed method, classifiers learned from "vehicle" training samples and "nonvehicle" training samples are used to enable recognition. We also propose a novel classification method, the "multiclustered modified quadratic discriminant function" (MC-MQDF). The MC-MQDF is capable of estimating the complex distribution due to the variety of different possible appearances for preceding vehicles. In order to confirm the feasibility of recognizing various vehicles, and to demonstrate the advantage of the MC-MQDF over the MQDF, classification experiments were carried out using the images of various vehicles. In a complex distribution test including a variety of vehicles, the classification rate for the MC-MQDF was approximately 98%, whereas the classification rate for the ordinary MQDF technique was approximately 93%. This supports the superiority of the MC-MQDF technique over the MQDF technique, and demonstrates the feasibility of recognizing a variety of different vehicles.

Comparison between infrared-image-based and visible-image-based approaches for pedestrian detection

Abstract: In order to improve the safety of night driving, automatic pedestrian detection has received more and more attraction. Since reliability is the most important issue in these systems, multi-dimensional-feature-based segmentation and classification needs to be introduced, and each axis should be efficient and be as much independent (to each other) as possible. To choose effective multi-dimensional features for infrared-image-based detection, the paper first investigates the possibilities of reusing available features for visible images by analyzing the different properties of infrared images and visible images. To take advantage of unique properties of infrared images, we propose the following novel features: special projection feature for segmentation, and two-axis pixel-distribution feature for classification. The segmentation based on new features does not depend on many assumptions and is shape-independent, thus avoiding brute-force multiple templates and multi-scale pyramid searching. The novel classification features include histogram feature and inertial feature that are independent and complimentary, thus the two-dimensional fusion-based classification significantly improves detection accuracy. These proposed features are independent from conventional pixel-array feature, and can be further fused with other general pedestrian detection features to improve simplicity, speed, and reliability.

Time to Contact Relative to a Planar Surface

Abstract: We show how to determine the time to contact from time varying images using only accumulated sums of suitable products of image brightness derivatives. There is no need for feature or object detection, tracking of features, estimation of optical flow, or any "higher level" processing. This so-called "direct" method for determining the time to contact is based on analysis of the motion field resulting from rigid body motion under perspective projection and the constant brightness assumption. The method has essentially no latency, since it can be based on analysis of just two frames of a video sequence, and does not require a calibrated camera. An implementation of the method is demonstrated on synthetic image sequences and stop motion sequences - where the ground truth is accurately know - as well as on video sequences taken by a camera mounted on moving vehicles.

Fast Feature Pyramids for Object Detection

Abstract: Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottleneck of many modern detectors is the computation of features at every scale of a finely-sampled image pyramid. Our key insight is that one may compute finely sampled feature pyramids at a fraction of the cost, without sacrificing performance: for a broad family of features we find that features computed at octave-spaced scale intervals are sufficient to approximate features on a finely-sampled pyramid. Extrapolation is inexpensive as compared to direct feature computation. As a result, our approximation yields considerable speedups with negligible loss in detection accuracy. We modify three diverse visual recognition systems to use fast feature pyramids and show results on both pedestrian detection (measured on the Caltech, INRIA, TUD-Brussels and ETH data sets) and general object detection (measured on the PASCAL VOC). The approach is general and is widely applicable to vision algorithms requiring fine-grained multi-scale analysis. Our approximation is valid for images with broad spectra (most natural images) and fails for images with narrow band-pass spectra (e.g., periodic textures).

Robot vision

Abstract: A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

System and method for monitoring and controlling remote devices

Abstract: The present invention is generally directed to a system for monitoring a variety of environmental and/or other conditions within a defined remotely located region. In one aspect, a system is configured to monitor utility meters (613) in a defined area. The system is implemented by using a plurality of wireless transmitters (614), each integrated into a sensor (612) adapted to monitor a particular data input. The system also includes a plurality of transceivers (221) that are dispersed throughout the region at defined locations. The system uses a local gateway (210) to translate and transfer information from the transmitters to a dedicated computer (260) on a network (230). The dedicated computer collects, compiles and stores the data for retrieval upon client demand across the network. The computer further includes means for evaluating the received information and identifying an appropriate control signal to be applied at a designated actuator.

Imaging system for vehicle

Abstract: An imaging system for a vehicle includes an imaging device having a field of view exteriorly and forward of the vehicle in its direction of travel, and an image processor operable to process the captured images in accordance with an algorithm. The algorithm comprises a sign recognition routine and a character recognition routine. The image processor processes the image data captured by the imaging device to detect signs in the field of view of the imaging device and applies the sign recognition routine to determine a sign type of the detected sign. The image processor is operable to apply the character recognition routine to the image data to determine information on the detected sign. The image processor applies the character recognition routine to the captured images in response to an output of the sign recognition routine being indicative of the detected sign being a sign type of interest.

On-road vehicle detection: a review

Abstract: Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments, and possible collision with other vehicles has attracted a lot of attention lately. In these systems, robust and reliable vehicle detection is a critical step. This paper presents a review of recent vision-based on-road vehicle detection systems. Our focus is on systems where the camera is mounted on the vehicle rather than being fixed such as in traffic/driveway monitoring systems. First, we discuss the problem of on-road vehicle detection using optical sensors followed by a brief review of intelligent vehicle research worldwide. Then, we discuss active and passive sensors to set the stage for vision-based vehicle detection. Methods aiming to quickly hypothesize the location of vehicles in an image as well as to verify the hypothesized locations are reviewed next. Integrating detection with tracking is also reviewed to illustrate the benefits of exploiting temporal continuity for vehicle detection. Finally, we present a critical overview of the methods discussed, we assess their potential for future deployment, and we present directions for future research.