Papers
Topics
Authors
Recent
Search
2000 character limit reached

TSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit

Published 1 Apr 2024 in cs.CV and cs.AI | (2404.00855v1)

Abstract: Detecting small moving objects in complex backgrounds from an overhead perspective is a highly challenging task for machine vision systems. As an inspiration from nature, the avian visual system is capable of processing motion information in various complex aerial scenes, and its Retina-OT-Rt visual circuit is highly sensitive to capturing the motion information of small objects from high altitudes. However, more needs to be done on small object motion detection algorithms based on the avian visual system. In this paper, we conducted mathematical modeling based on extensive studies of the biological mechanisms of the Retina-OT-Rt visual circuit. Based on this, we proposed a novel tectum small object motion detection neural network (TSOM). The neural network includes the retina, SGC dendritic, SGC Soma, and Rt layers, each layer corresponding to neurons in the visual pathway. The Retina layer is responsible for accurately projecting input content, the SGC dendritic layer perceives and encodes spatial-temporal information, the SGC Soma layer computes complex motion information and extracts small objects, and the Rt layer integrates and decodes motion information from multiple directions to determine the position of small objects. Extensive experiments on pigeon neurophysiological experiments and image sequence data showed that the TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Spatiotemporal energy models for the perception of motion. Josa a 2, 284–299. DOI:10.1364/JOSAA.2.000284.
  2. Visual acuity and the evolution of signals. Trends in ecology & evolution 33, 358–372. DOI:10.1016/j.tree.2018.03.001.
  3. Motion processing with wide-field neurons in the retino-tecto-rotundal pathway. Journal of computational neuroscience 28, 47–64. DOI:10.1007/s10827-009-0186-y.
  4. Pattern classification and scene analysis. volume 3. Wiley New York. https://www.svms.org/classification/DuHS95.pdf.
  5. Query by image and video content: The qbic system. computer 28, 23–32. DOI:10.1109/2.410146.
  6. Moving background patterns reveal double-opponency of directionally specific pigeon tectal neurons. Experimental brain research 43, 173–185. DOI:10.1007/BF00237761.
  7. Background subtraction in real applications: Challenges, current models and future directions. Computer Science Review 35, 100204. DOI:10.1016/j.cosrev.2019.100204.
  8. A moving target detection model inspired by spatio-temporal information accumulation of avian tectal neurons. Mathematics 11, 1169. DOI:10.3390/math11051169.
  9. Background subtraction for moving object detection: explorations of recent developments and challenges. The Visual Computer 38, 4151–4178. DOI:10.1007/s00371-021-02286-0.
  10. The optic tectum: a structure evolved for stimulus selection. DOI:10.1016/B978-0-12-804042-3.00016-6.
  11. Exploring optical-flow-guided motion and detection-based appearance for temporal sentence grounding. IEEE Transactions on Multimedia DOI:10.1109/TMM.2023.3238514.
  12. Infrared small and dim target detection with transformer under complex backgrounds. IEEE Transactions on Image Processing 32, 5921–5932. DOI:10.1109/TIP.2023.3326396.
  13. Msrmnet: Multi-scale skip residual and multi-mixed features network for salient object detection. Neural Networks 173, 106144. DOI:10.1016/j.neunet.2024.106144.
  14. An iterative image registration technique with an application to stereo vision, in: IJCAI’81: 7th international joint conference on Artificial intelligence, pp. 674–679. DOI:10.1371/journal.pone.0059298.
  15. Bottlebrush dendritic endings and large dendritic fields: motion-detecting neurons in the tectofugal pathway. Journal of Comparative Neurology 396, 399–414. DOI:10.1002/(SICI)1096-9861(19980706)396:3<399::AID-CNE9>3.0.CO;2-Y.
  16. Chattering and differential signal processing in identified motion-sensitive neurons of parallel visual pathways in the chick tectum. Journal of Neuroscience 21, 6440–6446. DOI:10.1523/JNEUROSCI.21-16-06440.2001.
  17. Sparse spatial sampling for the computation of motion in multiple stages. Biological Cybernetics 94, 276–287. DOI:10.1007/s00422-005-0046-4.
  18. Spatial organization of the pigeon tectorotundal pathway: an interdigitating topographic arrangement. Journal of Comparative Neurology 458, 361–380. DOI:10.1002/cne.10591.
  19. Attentional feature pyramid network for small object detection. Neural Networks 155, 439–450. DOI:10.1016/j.neunet.2022.08.029.
  20. Lateral inhibitory interactions in the intermediate layers of the monkey superior colliculus. Journal of Neurophysiology 79, 1193–1209. DOI:10.1152/jn.1998.79.3.1193.
  21. Global inhibition and stimulus competition in the owl optic tectum. Journal of Neuroscience 30, 1727–1738. DOI:10.1523/JNEUROSCI.3740-09.2010.
  22. Signaling of the strongest stimulus in the owl optic tectum. Journal of Neuroscience 31, 5186–5196. DOI:10.1523/JNEUROSCI.4592-10.2011.
  23. Modelling adaptation to directional motion using the adelson-bergen energy sensor. PloS one 8, e59298. DOI:10.1371/journal.pone.0059298.
  24. The effects of lesions of telencephalic visual structures on visual discriminative performance in turtles (chrysemyspicta picta). Journal of Comparative Neurology 218, 1–24. DOI:10.1002/cne.902180102.
  25. Center-surround organisation and interactions in receptive fields of goldfish tectal units. Vision research 19, 459–467. DOI:10.1016/0042-6989(79)90113-5.
  26. Space coding by gamma oscillations in the barn owl optic tectum. Journal of Neurophysiology 105, 2005–2017. DOI:10.1152/jn.00965.2010.
  27. Adaptive background mixture models for real-time tracking, in: Proceedings. 1999 IEEE computer society conference on computer vision and pattern recognition (Cat. No PR00149), IEEE. pp. 246–252. DOI:10.1109/CVPR.1999.784637.
  28. The merging of the senses. MIT press.
  29. Bsuv-net 2.0: Spatio-temporal data augmentations for video-agnostic supervised background subtraction. IEEE Access 9, 53849–53860. DOI:10.1109/ACCESS.2021.3071163.
  30. Mapping of the receptive fields in the optic tectum of chicken (gallus gallus) using sparse noise. PLoS One 8, e60782. DOI:10.1371/journal.pone.0060782.
  31. Neuronal responses to motion and apparent motion in the optic tectum of chickens. Brain Research 1635, 190–200. DOI:10.1016/j.brainres.2016.01.022.
  32. [dataset]Hongxin Wang, 2020. Rist data set.[online]. Available: https://sites.google.com/view/hongxinwang-personalsite/download.
  33. A directionally selective small target motion detecting visual neural network in cluttered backgrounds. IEEE transactions on cybernetics 50, 1541–1555. DOI:10.1109/TCYB.2018.2869384.
  34. A robust visual system for small target motion detection against cluttered moving backgrounds. IEEE transactions on neural networks and learning systems 31, 839–853. DOI:10.1109/TNNLS.2019.2910418.
  35. Attention and prediction-guided motion detection for low-contrast small moving targets. IEEE Transactions on Cybernetics DOI:10.1109/TCYB.2022.3170699.
  36. Neural coding model for fast and significant perceptual in the pigeon optic tectum. Journal of System Simulation 30, 4086–4099. DOI:10.16182/j.issn1004731x.joss.201811006.
  37. Encoding model for continuous motion-sensitive neurons in the intermediate and deep layers of the pigeon optic tectum. Neuroscience 484, 1–15. DOI:10.1016/j.neuroscience.2021.12.042.
  38. Moving object detection and marking based on frame difference and train algorithm for teaching video, in: 2021 IEEE 15th International Conference on Anti-counterfeiting, Security, and Identification (ASID), IEEE. pp. 61–65. DOI:10.1109/ASID52932.2021.9651485.
  39. Model of human visual-motion sensing. JOSA A 2, 322–342. DOI:10.1364/JOSAA.2.000322.
  40. A model for the detection of moving targets in visual clutter inspired by insect physiology. PloS one 3, e2784. DOI:10.1371/journal.pone.0002784.
  41. The optic tectum of birds: mapping our way to understanding visual processing. Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale 63, 328. DOI:10.1037/a0016826.
  42. Shufflenet: An extremely efficient convolutional neural network for mobile devices, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6848–6856. DOI:10.1109/CVPR.2018.00716.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up