Breakout Session Report: Spatiotemporal Grouping

Comparing biological and artificial vision systems: Network measures of functional connectivity

SUMMARYComputer Vision is essentially concerned with emulating the process of seeing, naturally manifested in various higher biological systems,1–4 on a computational apparatus, and is consequently part of the Artificial Intelligence field within the sub-category of Machine perception. Seeing has to do with making sense of image data acquired through an optical system and subsequently dealt with at increasing levels of abstraction and association with known facts about the world. The spectrum of interest in Computer Vision ranges from attempting to answer basic questions concerning the functionality of biological vision systems, particularly human, at one end, all the way to enhancing the reliability, speed and cost effectiveness of specific industrial operations, particularly component inspection and vision driven robotic manipulation. The main bulk of interest is in the middle, where the quest for generality pushes interest towards biological vision systems with their demonstrated effectiveness in a wide range of environments, some hostile, whilst the need for economic viability and timeliness in relation to particular application pushes interest towards finding workable algorithms which function reliably at high speed on affordable apparatus.This paper is addressed, in somewhat tutorial style, at clarifying, by examples of work in the area, the issues surrounding application oriented robotic vision systems, their assumptions, strengths, weaknesses and degree of generality, and at the same time putting them in the context of the overall field of Computer Vision. In addition, the paper points to directions of development which promise to provide powerful industrial vision tools at an acceptable price.

Human kind is exposed to large amounts of data. According to statistics, more than 80% of information received by humans comes from the visual system. Therefore, image information processing is not only an important research topic but also a challenging task. The unique information processing mechanism of the human visual system provides it with fast, accurate, and efficient image processing capabilities. At present, many advanced image analysis and processing techniques have been widely used in image communication, geographic information systems, medical image analysis, and virtual reality. However, there is still a large gap between these technologies and the human visual system. Therefore, building an image system research mechanism based on the biological vision system is an attractive but difficult target. Although it is a challenge, it can also be considered as an opportunity which utilizes biologically inspired ideas. Meanwhile, through the integration of neural biology, biological perception mechanisms, and computer science and mathematical science, related research can bridge biological vision and computer vision. Finally, the biologically inspired image analysis and processing system is expected to be built on the basis of further consideration of the learning mechanism of the human brain.

The detection of intensity changes by computer and biological vision systems

I.8 - Two-Dimensional Maps and Biological Vision: Representing Three-Dimensional Space

Human recognition is a practical field in Computer Vision and lot of research has been done on this field. In this paper we analyzed human recognition with new method which based on features that inspired from biological vision system. Here is shown that this method has good performance on human recognition and could be counted on as a reliable method in this field. Besides, it proposed a change in this method to have good trade-off between elapsed time to learn features and its performance to recognize a human in digital images.

There have been many researches on computer vision of diverse complex vision algorithms. However, despite its effectiveness, computer vision algorithm sometimes lacks the robustness of mammalian visual system for the application in dynamic environments in vehicle driving or outdoors. We have proposed that the neuromorphic visual processing algorithm based on the biological vision system is an effective approach for making detection of human objects on the road and inside the car. The effectiveness of proposed neuromorphic networks of visual processing is evaluated for the advanced driver assistance and pedestrian safety technology via the 99% of successful detection rate. The enhanced frame based neuromorphic processing showed that further applications could be sought from incorporating neuromorphic visual processing into Driver State Monitoring for the purpose of enhancing driving safety.

In the real world, the biological visual system is more efficient than the machine visual system in analyzing visual information. Physiology theories show that this efficiency owes to the multi-layer neural network in human visual system, in which every layer accomplishes different tasks and is related with other layers. The low-level stages of the human visual system, especially the retina, can provide certain scale information for the high-level stages of visual system through using the non-classical receptive field (nCRF) mechanism. This mechanism that the nCRF size can be adjusted automatically by ganglion cell (GC) can achieve a multi-scale image analysis. The results, reflecting the distribution of the image information, can be shared by several algorithms or processes solving different visual tasks, such as contour detection and image segmentation. A model of multi-scale image analysis based on GC has been proposed in this paper, which retains the key information and reduces the redundancy information for the further stages of the visual system. Experimental results on N-cut and contour detection show that this multi-scale image analysis model provides distinctive improvement for these image processing tasks.

In this study, we proposed a basic system using the simple analog circuit for motion detection based on the biological vision system and the mobile robot. The test circuit was fabricated on the breadboard by using discrete metal oxide semiconductor (MOS) transistors. The simulation results and the measured results of the test circuit showed that the motion detection circuit can output the motion signal. The test circuit was connected with the microcomputer introduced in the mobile robot, and the motion signal was input to the microcomputer. It was clarified from the measured results that the motion detection circuit can control the mobile robot.

We have proposed an analog motion detection circuit based on a biological vision system. A charge coupled device (CCD) camera was used as the input in order to obtain an input image. By using the CCD camera, it is possible to detect the movement of an object as a high-resolution image. Because the unit motion detection circuit is constructed with eight metal oxide semiconductor (MOS) transistors and one capacitor, the structure of the unit circuit is simple. The test circuit was constructed on a circuit board using discrete MOS transistors. The results from the test circuit showed that it can detect the direction of motion. The test circuit was connected to a microcomputer in a mobile robot. It was clear from the results that the motion detection circuit can control a mobile robot.

An analog motion detection circuit was proposed based on the biological vision system. A charge coupled device (CCD) camera was used as the input to obtain an input image. It is possible to detect the movement of an object as a high-resolution image by using the CCD camera. The proposed unit circuit is constructed with the pre-processing circuit and the motion detection circuit. The unit circuit is constructed with eighteen metal oxide semiconductor (MOS) transistors and one capacitor. The structure of the unit circuit is simple. The test circuit of the unit circuit was fabricated on the breadboard using discrete MOS transistors. The measured results of the test circuit showed that the proposed circuit can generate the signal for detecting the motion direction. The test circuit of the array constructed with twenty unit circuits was fabricated on the printed board. The measured results of the test array showed that the proposed circuit can detect the motion direction of the input image. It is clarified from the measured results that the proposed circuit can use as the new motion sensor.

A three-layer neural network is presented as a generic approach for visual pattern recognition invariant with respect to the geometric appearance such as translation, orientation and scale of the patterns. The invariant recognition is achieved by representing the geometric variations internally in the network by nodes in the input and middle layers, which are laterally connected and trained by a hybrid algorithm combining both competitive and Hebbian learning. As the result of the hybrid learning, each pattern will be represented by a particular subset of middle-layer nodes all specialized to respond to the same pattern but with different geometric appearances. The nodes in the output layer are then trained by competitive learning to recognize the different pattern internally represented by the middle-layer nodes, independent of their location, orientation and size. The proposed algorithm is generic and robust and can be applied to various practical recognition problems. Moreover, the network is relatively simple and biologically plausible and can serve as a computational model to account for the invariant object recognition in the biological visual system.

Visual object recognition is a difficult problem that has been solved by biological visual systems. An approach to object recognition is described in which the image is segmented into parts using two simple, biologically-plausible mechanisms: a filtering operation to produce a large set of potential object “parts,” followed by a new type of network that searches among these part hypotheses to produce the simplest, most likely description of the image's part structure.

The primary technology of the infrared imaging seeker optoelectronic countermeasure system includes the automatic recognition and tracking of air targets. New complex infrared interference factors pose severe challenges to the ability of infrared thermal imaging seekers to identify and lock targets accurately. Despite significant recent advances, machine vision systems still lag substantially behind biological vision systems in terms of performance and robustness. The distinguishing feature of the brain is its ability to detect learned objects under various non-ideal situations. Inspired by the sensitivity of the dorsal visual pathway to object motion information, a graph convolutional network learning model is developed for aerial target recognition, called the adaptive graph reasoning method driven by motion flow model, which employs the predicted object optical flow information to promote the keypoint estimation performance. First, an adaptive graph fusion module is designed to establish an adaptation mechanism to generalize keypoint features from the regular network to the target skeleton graph model. Then, the optical flow estimation features are utilized to understand the graph reasoning of the target keypoint motion. Finally, we propose a aerial target pose estimation framework which effectively integrates the temporal cues across frames by combining the motion features of optical flow estimation, and effectively promotes the estimation accuracy of keypoints. Finally, our extensive experiments in the established aerial target flight infrared dataset show the efficiency of the presented model.

In this paper, an ultra-fast smart vision system-on-a-chip design is proposed to provide effective solutions for real time machine vision applications by taking advantages of recent advances in integrated sensing/processing designs, electronic neural networks, advanced microprocessors and sub- micron VLSI technology. The smart vision system mimics what is inherent in biological vision systems. It is programmable to perform vision processing in all levels such as image acquisition, image fusion, image analysis, and scene interpretation. A system-on-a-chip implementation of this smart vision system is shown to be feasible by integrating the whole system into a 3-cm by 3-cm chip design in a 0.18- micrometer CMOS technology. The system achieves one tea- operation-per-second computing power that is a two order-of- magnitude increase over the state-of-the-art microcomputer and DSP chips. Its high performance is due to massively parallel computing structures, high data throughput rates, fast learning capabilities, and advanced VLSI system-on-a-chip implementation. This highly integrated smart vision system can be used for various NASA scientific missions and other military, industrial or commercial vision applications.