Biological Visual Mechanism Research Articles

Bio-inspired multi-level interactive contour detection network

Encoding-decoding convolutional neural network structures have shown powerful performance in contour detection tasks, however, the design of models in the past seems to have little reference to physiological mechanisms, especially biological visual mechanisms. And physiological studies have shown that the visual system is efficient and accurate in the extraction of contour features. Meanwhile, when designing network models, researchers pay more attention to the impact of decoding networks on the performance of the models and pay little attention to the impact of encoding networks on the performance of the models. Therefore, in this paper, inspired by the effective mechanism of the biological vision system for contour detection, we combine it with convolutional neural net and self-attention mechanism to design a multi-level interaction contour detection model. We call it MI-Net. Among them, the multi-level interaction module is designed to simulate the transmission mechanism of visual information across the visual cortex and the feedback mechanism of visual information to realize the multi-level interaction of different levels of the encoding network, and then optimize each visual level to achieve the improvement of the performance of contour detection. The feature integration module is designed by simulating the feature integration function of the inferior temporal (IT) cortex. Multiple feature integration modules are combined into a decoding network to increase the feature integration capability of the decoding network. Experiments on publicly available datasets show that our proposed contour detection network has good performance.

AGDS: adaptive goal-directed strategy for swarm drones flying through unknown environments

This paper aims to address a challenging problem of a drone swarm for a specific mission by reaching a desired region, through an unknown environment. A bio-inspired flocking algorithm with adaptive goal-directed strategy (AGDS) is proposed and developed for the drones swarmed across unknown environments. Each drone employs a biological visual mechanism to sense obstacles in within local perceptible scopes. Task information of the destination is only given to a few specified drones (named as informed agents), rather than to all other individual drones (uninformed agents). With the proposed flocking swarm, the informed agents operate collectively with the remaining uninformed agents to achieve a common and overall mission. By virtue of numerical simulation, the AGDS and non-adaptive goal-directed strategy (non-AGDS) are both presented and evaluated. Experiments by flying six DJI Tello quadrotors indoor are conducted to validate the developed flocking algorithm. Additional validations within canyon-like complicated scenarios have also been carried out. Both simulation and experimental results demonstrate the efficiency of the proposed swarm flocking algorithm with AGDS.

受生物视觉“图形–背景”分辨机制启发的遥感影像水体信息提取方法

受生物视觉“图形–背景”分辨机制启发的遥感影像水体信息提取方法

Frequency-Domain Joint Motion and Disparity Estimation Using Steerable Filters

In this paper, the problem of joint disparity and motion estimation from stereo image sequences is formulated in the spatiotemporal frequency domain, and a novel steerable filter-based approach is proposed. Our rationale behind coupling the two problems is that according to experimental evidence in the literature, the biological visual mechanisms for depth and motion are not independent of each other. Furthermore, our motivation to study the problem in the frequency domain and search for a filter-based solution is based on the fact that, according to early experimental studies, the biological visual mechanisms can be modelled based on frequency-domain or filter-based considerations, for both the perception of depth and the perception of motion. The proposed framework constitutes the first attempt to solve the joint estimation problem through a filter-based solution, based on frequency-domain considerations. Thus, the presented ideas provide a new direction of work and could be the basis for further developments. From an algorithmic point of view, we additionally extend state-of-the-art ideas from the disparity estimation literature to handle the joint disparity-motion estimation problem and formulate an algorithm that is evaluated through a number of experimental results. Comparisons with state-of-the-art-methods demonstrate the accuracy of the proposed approach.

Analysis of retinal and cortical components of Retinex algorithms

Following Land and McCann’s first proposal of the Retinex theory, numerous Retinex algorithms that differ considerably both algorithmically and functionally have been developed. We clarify the relationships among various Retinex families by associating their spatial processing structures to the neural organizations in the retina and the primary visual cortex in the brain. Some of the Retinex algorithms have a retina-like processing structure (Land’s designator idea and NASA Retinex), and some show a close connection with the cortical structures in the primary visual area of the brain (two-dimensional L&M Retinex). A third group of Retinexes (the variational Retinex) manifests an explicit algorithmic relation to Wilson–Cowan’s physiological model. We intend to overview these three groups of Retinexes with the frame of reference in the biological visual mechanisms.

Visual-adaptation-mechanism based underwater object extraction

Due to the major obstacles originating from the strong light absorption and scattering in a dynamic underwater environment, underwater optical information acquisition and processing suffer from effects such as limited range, non-uniform lighting, low contrast, and diminished colors, causing it to become the bottleneck for marine scientific research and projects. After studying and generalizing the underwater biological visual mechanism, we explore its advantages in light adaption which helps animals to precisely sense the underwater scene and recognize their prey or enemies. Then, aiming to transform the significant advantage of the visual adaptation mechanism into underwater computer vision tasks, a novel knowledge-based information weighting fusion model is established for underwater object extraction. With this bionic model, the dynamical adaptability is given to the underwater object extraction task, making them more robust to the variability of the optical properties in different environments. The capability of the proposed method to adapt to the underwater optical environments is shown, and its outperformance for the object extraction is demonstrated by comparison experiments.

A Study on Image Representation Method Based on Biological Visual Mechanism

Image representation is a key issue among many image processing tasks. By considering the problems faced by current general image representation methods, such as excessive computing amount, sensitivity to noise, lack of self-adaptability etc, a novel image representation method based on biologic visual mechanisms is proposed in this paper. Through simulating the primary visual cortex to realize the sparse representation of outside image it also introduced the synchronization mechanism to make it more accordant with visual system. Finally the presented method was verified by applying it to compress natural images and digital literature images respectively. The result showed that this new representation method is better than the general sparse representation method on both aspects of compression ratio and noise sensitivity.

A model for image categorisation based on a biological visual mechanism

For integrating a visual attention mechanism and object recognition in the visual cortex we propose a novel biologically‐motivated computational model for image categorisation. We first extract the focus of attention using an image‐driven, bottom‐up attention model and then adjust it according to the principles of whole effect and centre preference. After that, we obtain the region of interest, depending on the characteristics of object spatial proximity and object similarity. Based on this we compute a set of position‐ and scale‐invariant C2 features and finally pool them into the standard classifier to achieve image categorisation. We test our model on an image database used in SIMPLIcity. The results suggest that our model can not only classify images effectively under various complex “clutters” but also that it needs only a few training samples.