A modified model for the Lobula Giant Movement Detector and its FPGA implementation

Abstract

Bio-inspired vision sensors are particularly appropriate candidates for navigation of vehicles or mobile robots due to their computational simplicity, allowing compact hardware implementations with low power dissipation. The Lobula Giant Movement Detector (LGMD) is a wide-field visual neuron located in the Lobula layer of the Locust nervous system. The LGMD increases its firing rate in response to both the velocity of an approaching object and the proximity of this object. It has been found that it can respond to looming stimuli very quickly and trigger avoidance reactions. It has been successfully applied in visual collision avoidance systems for vehicles and robots. This paper introduces a modified neural model for LGMD that provides additional depth direction information for the movement. The proposed model retains the simplicity of the previous model by adding only a few new cells. It has been simplified and implemented on a Field Programmable Gate Array (FPGA), taking advantage of the inherent parallelism exhibited by the LGMD, and tested on real-time video streams. Experimental results demonstrate the effectiveness as a fast motion detector.

Background visual motion affects responses of an insect motion-sensitive neuron to objects deviating from a collision course

“…Our data are consistent with other studies that show how the LCMD/DCMD pathway responds to looming with a characteristic increasing firing rate that peaks near the time of collision (Schlotterer 1977;Rind and Simmons 1992;Gabbiani et al1999;Gray et al 2001). While many studies provide evidence to explain biophysical mechanisms underlying network looming responses in this system (Gabbiani et al 1999;Berm udez i Badia et al 2010;Meng et al 2010;Yue and Rind 2013), we compare our work presented here to recent investigations into DCMD responses to changes in object trajectory and background motion complexity.…”

“…; Meng et al. ; Yue and Rind ), we compare our work presented here to recent investigations into DCMD responses to changes in object trajectory and background motion complexity.…”

Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review

“…The experimental data is adapted from [101]. model encoding onset and offset responses by luminance increments and decrements, adapted from [114], (b) a modified LGMD1 model for multiple looming objects detection, adapted from [233], (c) a simplified LGMD1 model for collision avoidance of an UAV, adapted from [188], (d) a modified LGMD1 model with enhancement of collision selectivity, adapted from [133,132], (e) a modified LGMD1 model with a new layer for noise reduction and spikingthreshold mediation, adapted from [198,197], (f) an LGMD1 neural network based on the modelling of elementary motion detectors for collision detection in ground vehicle scenarios, adapted from [91]. Based on this LGMD1 modelling theory, a good number of models have been produced during the past two decades; these works have not only been extending and consolidating the LGMD1's original functionality for looming perception, but also investigating the possible applications to mobile machines like robots and vehicles.…”

Bio-Inspired Embedded Vision System for Autonomous Micro-Robots: The LGMD Case

“…Badia et al [23] proposed one form of LGMD based collision detection model and tested it on a high-speed robot "Strider" with a wireless camera to capture and transmit images to PC for processing. Silva et al [33] proposed another modified LGMD model which combined two previous works from [19] and [34] for more robust collision detection, which focused more on modelling instead of embedded system development.…”

“…There has been effort on implementing bio-inspired method in VLSI chips like FPGA, for example, Meng et al [34] added additional cell to detect the movement in depth, Harrison [35] proposed an Analog IC for visual collision detection based on EMD, and Okuno and Yagi [36] implemented mixed analogdigital integrated circuits with FPGA. However, these attempts are not suitable for micro and mini robots, either because of the large size or the high power consumption of the FPGA circuits.…”