Bio-Inspired Neural Network for Collision Detection Based on Focus of Expansion

doi:10.19678/j.issn.1000-3428.0252184

Abstract

Abstract: Using traditional computer vision technology to solve collision detection problems in complex scenes is extremely difficult, particularly when dealing with false collision interference, where the model exhibits a high false alarm rate and low accuracy. To address this problem, this paper proposes a bio-inspired Enhanced Collision Detection Neural Network (ECDNN) that effectively reduces false collision interference in complex scenes. This network is developed based on the hierarchical structural characteristics of the mammalian retina by leveraging the danger perception properties of neurons in the Polysensory Zone (PZ) of the precentral gyrus in the primate cerebral cortex toward specific visual field regions. The network consists of two parts: a presynaptic neural subnetwork and a postsynaptic neural subnetwork. Specifically, the presynaptic subnetwork, which is based on the hierarchical processing and stepwise transmission characteristics of mammalian retinal information, perceives the global Focus of Expansion (FOE) from low-level visual information to divide the dynamic focus receptive field, thereby obtaining key visual information. The postsynaptic subnetwork integrates the membrane potential excitatory responses elicited by approaching visual stimuli within the focus-receptive field and outputs an alarm signal representing imminent collision danger. Experimental results show that the proposed model can effectively filter false collision interference in complex scenes, reduce false detections, and improve collision detection accuracy to over 96%. The study findings provide an important foundation for building future artificial intelligence interactive systems.

Key words: collision detection, false collision, Focus of Expansion (FOE), looming danger perception, membrane potential excitation, biological vision

摘要： 利用传统计算机视觉技术来解决复杂场景中的碰撞检测问题是一项十分艰巨的任务，尤其是面临虚碰撞干扰时模型误检率较高而准确率较低。针对该问题，本文基于哺乳动物视网膜分层结构特性，借助灵长类动物大脑皮层中央前回多感觉皮质区（PZ）神经元对特定视野区的危险感知特性，提出了一种能有效降低复杂场景中虚碰撞干扰的生物启发式增强碰撞检测神经网络（ECDNN）。该网络包含突触前和突触后两部分神经子网络结构。突触前子网络基于哺乳动物视网膜信息分层处理，逐级传递特性，从低阶视觉信息感知全局膨胀焦点（FOE）来划分动态聚焦感受野，以此获取关键视觉信息。突触后子网络整合聚焦感受野内由迫近视觉刺激引发的膜电位兴奋响应，输出表征迫近碰撞危险的警报信号。实验结果表明，该模型不仅能有效过滤复杂场景中虚碰撞干扰，降低模型误检，还将碰撞检测准确率提升至96%以上，可为构建人工智能交互系统提供重要基础。

关键词: 碰撞检测, 虚碰撞, 膨胀焦点, 迫近危险感知, 膜电位兴奋, 生物视觉

CLC Number:

TP391

PI Chengdong, HU Bin. Bio-Inspired Neural Network for Collision Detection Based on Focus of Expansion[J]. Computer Engineering, 2026, 52(11): 219-238.

皮成东, 胡滨. 基于膨胀焦点的生物启发碰撞检测神经网络[J]. 计算机工程, 2026, 52(11): 219-238.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0252184

https://www.ecice06.com/EN/Y2026/V52/I11/219

References

[1] JI X, ZHAO Y C, LU S, et al. Robot path tracking and real-time obstacle avoidance under laser radar technology[C]//Proceedings of the IEEE 5th International Conference on Power, Intelligent Computing and Systems (ICPICS). Washington D.C., USA: IEEE Press, 2023: 512-518.
[2] LI H R, KINSNER W, WANG Y, et al. Airborne radar based collision detection and avoidance system for unmanned aircraft systems in a varying environment[C]//Proceedings of the IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE). Washington D.C., USA: IEEE Press, 2021: 43-48.
[3] YASIN J N, MOHAMED S A S, HAGHBAYAN M H, et al. Low-cost ultrasonic based object detection and collision avoidance method for autonomous robots[J]. International Journal of Information Technology, 2021, 13(1): 97-107.
[4] YUE S G, RIND F C. Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement[J]. IEEE Transactions on Neural Networks, 2006, 17(3): 705-716.
[5] LI T, ZHAO Z G, ZHU M T, et al. Cable vector collision detection algorithm for multi-robot collaborative towing system[J]. Journal of Shanghai Jiaotong University (Science), 2025, 30(2): 319-329.
[6] WU J H, LIAO Z X, HAN Y, et al. An integral design for high performance sensor-less collision detection of serial robots[C]//Proceedings of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). Washington D.C., USA: IEEE Press, 2022: 1714-1721.
[7] HU B, ZHANG Z H. Bio-inspired visual neural network on spatio-temporal depth rotation perception[J]. Neural Computing and Applications, 2021, 33(16): 10351-10370.
[8] HU B, ZHANG Z H. Bio-plausible visual neural network for spatio-temporally spiral motion perception[J]. Neurocomputing, 2018, 310: 96-114.
[9] GRAZIANO M S A, COOKE D F. Parieto-frontal interactions, personal space, and defensive behavior[J]. Neuropsychologia, 2006, 44(6): 845-859.
[10] ZHAO J Y, XI S K, LI Y, et al. A fly inspired solution to looming detection for collision avoidance[J]. iScience, 2023, 26(4): 106337.
[11] ZHANG Z H, YUE S G, ZHANG G P. Fly visual system inspired artificial neural network for collision detection[J]. Neurocomputing, 2015, 153: 221-234.
[12] LI L, ZHANG Z H, LU J X. Artificial fly visual joint perception neural network inspired by multiple-regional collision detection[J]. Neural Networks, 2021, 135: 13-28.
[13] KATSAMPIRIS-SALGADO K, HANINGER K, GKRIZIS C, et al. Collision detection for collaborative assembly operations on high-payload robots[J]. Robotics and Computer-Integrated Manufacturing, 2024, 87: 102708.
[14] SHI C, DONG Z R, PUNDLIK S, et al. A hardware-friendly optical flow-based time-to-collision estimation algorithm[J]. Sensors, 2019, 19(4): 807.
[15] XIN X R, LIU K Z, YANG Z L, et al. A probabilistic risk approach for the collision detection of multi-ships under spatiotemporal movement uncertainty[J]. Reliability Engineering & System Safety, 2021, 215: 107772.
[16] TRACY K, HOWELL T A, MANCHESTER Z. Differentiable collision detection for a set of convex primitives[C]//Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Washington D.C., USA: IEEE Press, 2023: 3663-3670.
[17] MONTAUT L, LE LIDEC Q, BAMBADE A, et al. Differentiable collision detection: a randomized smoothing approach[C]//Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Washington D.C., USA: IEEE Press, 2023: 3240-3246.
[18] HEIBERG A, LARSEN T N, MEYER E, et al. Risk-based implementation of COLREGs for autonomous surface vehicles using deep reinforcement learning[J]. Neural Networks, 2022, 152: 17-33.
[19] ALMUTAIRI M S, ALMUTAIRI K, CHIROMA H. Hybrid of deep recurrent network and long short term memory for rear-end collision detection in fog based Internet of vehicles[J]. Expert Systems with Applications, 2023, 213: 119033.
[20] ZHOU B H, LI Z F, et al. Shallow neural networks trained to detect collisions recover features of visual loom-selective neurons[J]. eLife, 2022, 11: e72067.
[21] RILL R A, FARAGÓ K B. Collision avoidance using deep learning-based monocular vision[J]. SN Computer Science, 2021, 2(5): 375.
[22] CHAN F H, CHEN Y T, XIANG Y, et al. Anticipating accidents in dashcam videos[C]//Proceedings of the ACCV 2016. Berlin, Germany: Springer, 2017: 136-153.
[23] BAO W T, YU Q, KONG Y. Uncertainty-based traffic accident anticipation with spatio-temporal relational learning[C]//Proceedings of the 28th ACM International Conference on Multimedia. New York, USA: ACM Press, 2020: 2682-2690.
[24] FU Q B, WANG H X, HU C, et al. Towards computational models and applications of insect visual systems for motion perception: a review[J]. Artificial Life, 2019, 25(3): 263-311.
[25] YAKUBOWSKI J M, MCMILLAN G A, GRAY J R. Background visual motion affects responses of an insect motion-sensitive neuron to objects deviating from a collision course[J]. Physiological Reports, 2016, 4(10): e12801.
[26] QIN Z Y, FU Q B, PENG J G. A computationally efficient and robust looming perception model based on dynamic neural field[J]. Neural Networks, 2024, 179: 106502.
[27] ZHENG Y, WANG Y S, WU G R, et al. Enhancing LGMD-based model for collision prediction via binocular structure[J]. Frontiers in Neuroscience, 2023, 17: 1247227.
[28] CHANG Z F, FU Q B, CHEN H, et al. A look into feedback neural computation upon collision selectivity[J]. Neural Networks, 2023, 166: 22-37.
[29] CHANG Z F, FU Q B, HUA M, et al. Feedback neural computation in collision perception: towards diverse selectivity[J]. Neurocomputing, 2024, 598: 128110.
[30] FU Q B, HU C, PENG J G, et al. Shaping the collision selectivity in a looming sensitive neuron model with parallel ON and OFF pathways and spike frequency adaptation[J]. Neural Networks, 2018, 106: 127-143.
[31] LI J T, SUN X L, LI H Y, et al. On the ensemble of collision perception neuron models towards ultra-selectivity[C]//Proceedings of the International Joint Conference on Neural Networks (IJCNN). Washington D.C., USA: IEEE Press, 2023: 1-8.
[32] FU Q B, HU C, PENG J G, et al. A robust collision perception visual neural network with specific selectivity to darker objects[J]. IEEE Transactions on Cybernetics, 2020, 50(12): 5074-5088.
[33] HONG J L, FU Q B, SUN X L, et al. Boosting collision perception against noisy signals with a probabilistic neural network[C]//Proceedings of the International Joint Conference on Neural Networks (IJCNN). Washington D.C., USA: IEEE Press, 2023: 1-8.
[34] CHANG Z F, CHEN H, HUA M, et al. A bio-inspired visual collision detection network integrated with dynamic temporal variance feedback regulated by scalable functional countering jitter streaming[J]. Neural Networks, 2025, 182: 106882.
[35] 章盛, 郑胜男, 沈洁, 等. 果蝇嗅视神经通路研究综述[J]. 电子与信息学报, 2024, 46(6): 2335-2351.ZHANG S, ZHENG S N, SHEN J, et al. Review on olfactory and visual neural pathways in drosophila[J]. Journal of Electronics & Information Technology, 2024, 46(6): 2335-2351. (in Chinese)
[36] GRAZIANO M S A, HU X T, GROSS C G. Visuospatial properties of ventral premotor cortex[J]. Journal of Neurophysiology, 1997, 77(5): 2268-2292.
[37] WANG X Y, GONG X M, SUN Q, et al. Attractive effects of previous form information on heading estimation from optic flow occur at perceptual stage[J]. Journal of Vision, 2022, 22(12): 18.
[38] STRONG S L, SILSON E H, GOUWS A D, et al. Differential processing of the direction and focus of expansion of optic flow stimuli in areas MST and V3A of the human visual cortex[J]. Journal of Neurophysiology, 2017, 117(6): 2209-2217.
[39] HUANG R, ERICSON S. An efficient way to estimate the focus of expansion[C]//Proceedings of the IEEE 3rd International Conference on Image, Vision and Computing (ICIVC). Washington D.C., USA: IEEE Press, 2018: 691-695.
[40] HAHN J, MONAVARFESHANI A, QIAO M, et al. Evolution of neuronal cell classes and types in the vertebrate retina[J]. Nature, 2023, 624(7991): 415-424.
[41] 冯涛, 胡滨, 徐光源. 复杂场景下的生物启发人群逃逸检测神经网络[J]. 计算机工程, 2026, 52(9): 176-192.FENG T, HU B, XU G Y. Biologically inspired neural networks for crowd escape detection in complex scenes[J]. Computer Engineering, 2026, 52(9): 176-192. (in Chinese)
[42] 赵轻轻, 胡滨. 不变性全局稀疏轮廓点表征的运动行人检测神经网络[J]. 计算机应用, 2025, 45(4): 1271-1284.ZHAO Q Q, HU B. Moving pedestrian detection neural network with invariant global sparse contour point representation[J]. Journal of Computer Applications, 2025, 45(4): 1271-1284. (in Chinese)
[43] VLASITS A L, EULER T, FRANKE K. Function first: classifying cell types and circuits of the retina[J]. Current Opinion in Neurobiology, 2019, 56: 8-15.
[44] WEST E R, CEPKO C L. Development and diversification of bipolar interneurons in the mammalian retina[J]. Developmental Biology, 2022, 481: 30-42.
[45] 陈林果, 黄荣, 韩芳. 一种生物视觉启发的高鲁棒性脉冲循环神经网络模型[J]. 宁夏大学学报(自然科学版中英文), 2026, 47(1): 24-32. CHEN L G, HUANG R, HAN F. A highly robust spiking recurrent neural network model inspired by biological vision[J]. Journal of Ningxia University (Natural Science Edition in Chinese and English), 2026, 47(1): 24-32. (in Chinese)
[46] CALONDER M, LEPETIT V, STRECHA C, et al. BRIEF: binary robust independent elementary features[M]. Berlin, Germany: Springer, 2010: 778-792.
[47] SHAH A P, LAMARE J B, NGUYEN-ANH T, et al. CADP: a novel dataset for CCTV traffic camera based accident analysis[C]//Proceedings of the 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). Washington D.C., USA: IEEE Press, 2018: 1-9.
[48] MOURA D C, ZHU S Z, ZVITIA O. Nexar dashcam collision prediction dataset and challenge[EB/OL]. [2025-02-07]. https://arxiv.org/abs/2503.03848.
[49] GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving? The KITTI vision benchmark suite[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2012: 3354-3361.
[50] TEMIZER I, DONOVAN J C, BAIER H, et al. A visual pathway for looming-evoked escape in larval zebrafish[J]. Current Biology, 2015, 25(14): 1823-1834.
[51] WANG Y, GONG Y, HUANG S M, et al. Memristor-based biomimetic compound eye for real-time collision detection[J]. Nature Communications, 2021, 12: 5979.

Please choose a citation manager

Content to export