An Ego-Motion Detection System Employing Directional-Edge-Based Motion Field Representations

Abstract

SUMMARYIn this paper, a motion field representation algorithm based on directional edge information has been developed. This work is aiming at building an ego-motion detection system using dedicated VLSI chips developed for real time motion field generation at low powers [1], [2]. Directional edge maps are utilized instead of original gray-scale images to represent local features of an image and to detect the local motion component in a moving image sequence. Motion detection by edge histogram matching has drastically reduced the computational cost of block matching, while achieving a robust performance of the ego-motion detection system under dynamic illumination variation. Two kinds of feature vectors, the global motion vector and the component distribution vectors, are generated from a motion field at two different scales and perspectives. They are jointly utilized in the hierarchical classification scheme employing multiple-clue matching. As a result, the problems of motion ambiguity as well as motion field distortion caused by camera shaking during video capture have been resolved. The performance of the ego-motion detection system was evaluated under various circumstances, and the effectiveness of this work has been verified.

A Real-Time Motion-Feature-Extraction VLSI Employing Digital-Pixel-Sensor-Based Parallel Architecture

“…However, the VLSI architecture introduced in this paper can also be used in analyzing images having moving backgrounds. For example, for the ego-motion analyzing algorithms developed in [63] and [73], the computationally expensive GFE procedure can be efficiently carried out using the chip in this paper. In addition, the self-speed-adaptive (or the so-called automatic speed adaptation in [63] and [73]) procedure can be efficiently achieved using the architecture developed in the MFE module.…”

“…For example, for the ego-motion analyzing algorithms developed in [63] and [73], the computationally expensive GFE procedure can be efficiently carried out using the chip in this paper. In addition, the self-speed-adaptive (or the so-called automatic speed adaptation in [63] and [73]) procedure can be efficiently achieved using the architecture developed in the MFE module. Such ego-motion information is very helpful for analyzing images with moving backgrounds.…”

“…Besides the still image analysis, a directional-edge-based object tracking algorithm is also proposed in [58] with its FPGA implementation in [59], in which a speed of 150 frames/s was experimentally demonstrated, and a speed of 900 frames/s was expected if the algorithm was directly implemented on VLSI with an on-chip image sensor. The succeeding works [60]- [63] further developed edge-based motion recognition algorithms in which the self-speed-adaptive MFE processing is included as one of the most crucial steps. Although VLSI chips for post-MFE optical flow detection [64], [65] and pattern recognition [55], [56], [66]- [68] have been implemented, a VLSI dedicated to high-speed and low-power MFE has not yet been developed.…”

“…The measurement results show that this chip can perform MFE within 0.9 ms after capturing the image when running at 20 MHz at a power consumption of 9 mW. The directional-edge-based features generated by this chip can be used for motion recognition [60]- [63] as well as for still image recognition [49], [50] and object tracking [58], [59]. An object detecting system is also developed using the fabricated chip.…”

A row-parallel cyclic-line-access edge detection CMOS image sensor employing global thresholding operation

“…The global thresholding algorithm has been proposed as a promising candidate for such a purpose [11] and its effectiveness is demonstrated in image recognition as well as in object tracking [12] and action recognition [13]. In this algorithm, the threshold value is adaptively determined so that a certain predetermined number of edges are retained in the image having larger gradient values.…”