Dynamic Signal Suppression Increases the Fidelity of Looming Perception Against Input Variability

The perception of looming objects moving in depth is a basis of artificially dynamic vision system, which has been widely used in robots for autonomous obstacle detection-and-avoidance. How to reliably detect looming objects in chaotic environments is prerequisite, however, still a challenging problem. The current looming perception models or neural networks are greatly affected by input variability on visual contrast between looming object and its background. In this case, the responses of looming detection neurons in animals are robust, which suggests that contrast cues are well encoded in biological visual neural pathways. Considering the physiological homology between Drosophila and locust, this paper draws lessons from the progress of Drosophila physiology to improve the current locust-inspired looming perception model. Two contrast computation schemes herein are proposed: (1) In the early stage of visual processing, the instantaneous feedback mechanism based contrast normalisation dynamically suppress the preliminary motion signals with respect to time. (2) In the later stage of processing, a parallel channel dedicated to calculating local contrast of motion signal is converged to weaken high-contrast signals. Through the comparative tests against many pure and natural scenes, the proposed method works effectively and robustly to reduce fluctuation and variance of response against high input variability on contrast. Here we highlight the effectiveness of temporally dynamic suppression to motion signals in the proposed neural network model, which significantly improves the fidelity of looming perception. This study also shows its competitiveness in the repository of bio-inspired looming perception models.