A Time-Delay Feedback Neural Network for Discriminating Small,
Fast-Moving Targets in Complex Dynamic Environments
- URL: http://arxiv.org/abs/2001.05846v5
- Date: Mon, 28 Jun 2021 02:02:51 GMT
- Title: A Time-Delay Feedback Neural Network for Discriminating Small,
Fast-Moving Targets in Complex Dynamic Environments
- Authors: Hongxin Wang, Huatian Wang, Jiannan Zhao, Cheng Hu, Jigen Peng and
Shigang Yue
- Abstract summary: Discriminating small moving objects within complex visual environments is a significant challenge for autonomous micro robots.
We propose an STMD-based neural network with feedback connection (Feedback STMD), where the network output is temporally delayed, then fed back to the lower layers to mediate neural responses.
- Score: 8.645725394832969
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Discriminating small moving objects within complex visual environments is a
significant challenge for autonomous micro robots that are generally limited in
computational power. By exploiting their highly evolved visual systems, flying
insects can effectively detect mates and track prey during rapid pursuits, even
though the small targets equate to only a few pixels in their visual field. The
high degree of sensitivity to small target movement is supported by a class of
specialized neurons called small target motion detectors (STMDs). Existing
STMD-based computational models normally comprise four sequentially arranged
neural layers interconnected via feedforward loops to extract information on
small target motion from raw visual inputs. However, feedback, another
important regulatory circuit for motion perception, has not been investigated
in the STMD pathway and its functional roles for small target motion detection
are not clear. In this paper, we propose an STMD-based neural network with
feedback connection (Feedback STMD), where the network output is temporally
delayed, then fed back to the lower layers to mediate neural responses. We
compare the properties of the model with and without the time-delay feedback
loop, and find it shows preference for high-velocity objects. Extensive
experiments suggest that the Feedback STMD achieves superior detection
performance for fast-moving small targets, while significantly suppressing
background false positive movements which display lower velocities. The
proposed feedback model provides an effective solution in robotic visual
systems for detecting fast-moving small targets that are always salient and
potentially threatening.
Related papers
- TSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit [4.640328175695991]
The Retina-OT-Rt visual circuit is highly sensitive to capturing the motion information of small objects from high altitudes.
We propose a novel tectum small object motion detection neural network (TSOM)
The TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.
arXiv Detail & Related papers (2024-04-01T01:49:08Z) - PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search [64.28335667655129]
Multiple object tracking is a critical task in autonomous driving.
As tracking accuracy improves, neural networks become increasingly complex, posing challenges for their practical application in real driving scenarios due to the high level of latency.
In this paper, we explore the use of the neural architecture search (NAS) methods to search for efficient architectures for tracking, aiming for low real-time latency while maintaining relatively high accuracy.
arXiv Detail & Related papers (2024-03-23T04:18:49Z) - SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small
Target Detector [60.42293239557962]
We propose SpirDet, a novel approach for efficient detection of infrared small targets.
We employ a new dual-branch sparse decoder to restore the feature map.
Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models.
arXiv Detail & Related papers (2024-02-08T05:06:14Z) - Spatio-Temporal Feedback Control of Small Target Motion Detection Visual
System [9.03311522244788]
This paper develops a visual system withtemporal-temporal feedback to detect small target motion.
The proposed visual system is composed of two complementary spatial neuronalworks.
Experimental results demonstrate that the system is more competitive than existing methods in detecting small targets.
arXiv Detail & Related papers (2022-11-18T10:10:48Z) - Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value
Functions [65.84090965167535]
We present Neural Motion Fields, a novel object representation which encodes both object point clouds and the relative task trajectories as an implicit value function parameterized by a neural network.
This object-centric representation models a continuous distribution over the SE(3) space and allows us to perform grasping reactively by leveraging sampling-based MPC to optimize this value function.
arXiv Detail & Related papers (2022-06-29T18:47:05Z) - Infrared Small-Dim Target Detection with Transformer under Complex
Backgrounds [155.388487263872]
We propose a new infrared small-dim target detection method with the transformer.
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
We also design a feature enhancement module to learn more features of small-dim targets.
arXiv Detail & Related papers (2021-09-29T12:23:41Z) - An Attention and Prediction Guided Visual System for Small Target Motion
Detection in Complex Natural Environments [7.972704756263765]
Small target motion detection within complex natural environment is an extremely challenging task for autonomous robots.
In this paper, we propose an attention and prediction guided visual system to overcome this limitation.
The proposed visual system mainly consists of three subsystems, including an attention module, a STMD-based neural network, and a prediction module.
arXiv Detail & Related papers (2021-04-27T07:42:31Z) - Continuity-Discrimination Convolutional Neural Network for Visual Object
Tracking [150.51667609413312]
This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN) for visual object tracking.
To address this problem, CD-CNN models temporal appearance continuity based on the idea of temporal slowness.
In order to alleviate inaccurate target localization and drifting, we propose a novel notion, object-centroid.
arXiv Detail & Related papers (2021-04-18T06:35:03Z) - A Bioinspired Approach-Sensitive Neural Network for Collision Detection
in Cluttered and Dynamic Backgrounds [19.93930316898735]
Rapid accurate and robust detection of looming objects in moving backgrounds is a significant and challenging problem for robotic visual systems.
Inspired by the neural circuit elementary vision in the mammalian retina, this paper proposes a bioinspired approach-sensitive neural network (AS)
The proposed model is able to not only detect collision accurately and robustly in cluttered and dynamic backgrounds but also extract more collision information like position and direction, for guiding rapid decision making.
arXiv Detail & Related papers (2021-03-01T09:16:18Z) - A Bioinspired Retinal Neural Network for Accurately Extracting
Small-Target Motion Information in Cluttered Backgrounds [19.93930316898735]
This paper proposes a bioinspired neural network based on a new neuro-based motion filtering and multiform 2-D spatial filtering.
It can estimate motion direction accurately via only two signals and respond to small targets of different sizes and velocities.
It can also extract the information of motion direction and motion accurately energy and rapidly.
arXiv Detail & Related papers (2021-03-01T08:44:27Z) - Fast Motion Understanding with Spatiotemporal Neural Networks and
Dynamic Vision Sensors [99.94079901071163]
This paper presents a Dynamic Vision Sensor (DVS) based system for reasoning about high speed motion.
We consider the case of a robot at rest reacting to a small, fast approaching object at speeds higher than 15m/s.
We highlight the results of our system to a toy dart moving at 23.4m/s with a 24.73deg error in $theta$, 18.4mm average discretized radius prediction error, and 25.03% median time to collision prediction error.
arXiv Detail & Related papers (2020-11-18T17:55:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.