Robust scene recognition using a GA and real-world raw-image

Electron Comm Jpn Pt III

2005

Self Cite

SUMMARYIn ITS, there has recently been emphasis on the importance of developing a driving assistance system which can detect pedestrians with a car-mounted camera and warn of their presence in order to assure pedestrian safety. In particular, the ability to detect multiple pedestrians in real time (at a video rate of 30 fps) is indispensable from the practical point of view. Consequently, this study proposes a method of recognizing multiple moving objects (pedestrians) in real time using dynamic scene input from a car-mounted camera, as a basic technology for the driving assistance system. The presence of a pedestrian is evaluated on the basis of hue information in the HSI color representation system and model-based matching using a circular approximation model. Thus, in terms of the evaluation function, the problem of recognition of multiple pedestrians is replaced by the problem of search for multiple local maxima. However, it is difficult to realize the process in real time if the evaluation value is calculated for the whole image. This paper considers the "attention," which is a function that reduces the burden of human visual information processing, and proposes a method in which a pseudoattention function is realized by using a hybrid GA, allowing multiple local maxima to be retrieved efficiently in real time.A real-time experiment on the recognition of multiple pedestrians in dynamic images obtained from a carmounted camera was used to verify the effectiveness of the proposed method. In addition, the practical performance of the system was investigated by an experiment on the recognition of suddenly appearing pedestrians.

Section: Evaluation Of Human Image By Color and Shape Informationmentioning

confidence: 99%

“…The presence of pedestrians is evaluated by modelbased matching [11] based on hue information in the HSI color representation system [10]. A circular approximation model is used as the shape evaluation model.…”

Section: Introductionmentioning

confidence: 99%

Real‐time recognition of multiple pedestrians using car‐mounted camera

Suzuki

Electron Comm Jpn Pt III

2005

Self Cite

“…Therefore, in the whole on-line trajectory tracking process, always keeping the avoidance manipulability (see [5]) of whole manipulator high is very important. Based on this requirement of high avoidance manipulability, to optimize trajectory tracking and obstacle avoidance online, we adopt 1-step Genetic Algorithm (see [6]) considering potential spaces (see [7]) around the measured target object, to search real-time optimal configurations of the manipulator at future times. Then, we present multi-preview control for solving reachability problem according to the concept of preview control (see [8]).…”

Section: Introductionmentioning

confidence: 99%

Multi-preview configuration control for redundant manipulator by future reachability evaluation

Zhang

2007 IEEE/RSJ International Conference on Intelligent Robots and Systems

Song

2007

Self Cite

This paper proposes a new approach to achieve an on-line control of trajectory tracking and obstacle avoidance for redundant manipulators without prechecking path-planning in whole trajectory tracking. In the trajectory tarcking process, manipulator is required to keep a configuration with maximal avoidance manipulability in real-time. In this paper, we present a new idea: Multi-Preview Control, which uses several future optimal configurations to control current configuration to complete task of trajectory tracking and obstacle avoidance online with high avoidance manipulability and reachability. We verify the validity of multi-preview control through simulations of comparing single-preview control with multi-preview control.

“…Therefore, in the whole on-line trajectory tracking process, always keeping the avoidance manipulability (see [5]) of whole manipulator high is very important. Based on this requirement of high avoidance manipulability, to optimize trajectory tracking and obstacle avoidance on-line, we adopt 1-step Genetic Algorithm (see [6], [7]) considering potential spaces (see [8]) around the measured target object to search real-time optimal Fig. 2 The concept of single-preview control configurations of the manipulator at future times.…”

Section: Introductionmentioning

confidence: 99%

Multi-preview configuration control for redundant manipulator by future reachability evaluation

Zhang

SICE Annual Conference 2007

Song

2007

This paper proposes a new approach to achieve an on-line control of trajectory tracking and obstacle avoidance for redundant manipulators without prechecking path-planning in whole trajectory tracking. In the trajectory tarcking process, manipulator is required to keep a configuration with maximal avoidance manipulability in real-time. In this paper, we present a new idea: Multi-Preview Control, which uses several future optimal configurations to control current configuration to complete task of trajectory tracking and obstacle avoidance on-line with high avoidance manipulability and reachability. We verify the validity of multi-preview control through simulations of comparing single-preview control with multi-preview control.