A Robust Visual System for Small Target Motion Detection Against Cluttered Moving Backgrounds

Visually guided swarm motion coordination via insect-inspired small target motion reactions

Despite progress developing experimentally-consistent models of insect in-flight sensing and feedback for individual agents, a lack of systematic understanding of the multi-agent and group performance of the resulting bio-inspired sensing and feedback approaches remains a barrier to robotic swarm implementations. This study introduces the small-target motion reactive (STMR) swarming approach by designing a concise engineering model of the small target motion detector (STMD) neurons found in insect lobula complexes. The STMD neuron model identifies the bearing angle at which peak optic flow magnitude occurs, and this angle is used to design an output feedback switched control system. A theoretical stability analysis provides bi-agent stability and state boundedness in group contexts. The approach is simulated and implemented on ground vehicles for validation and behavioral studies. The results indicate despite having the lowest connectivity of contemporary approaches (each agent instantaneously regards only a single neighbor), STMR achieves collective group motion. STMR group level metric analysis also highlights continuously varying polarization and decreasing heading variance.

Detecting and Tracking of Multiple Mice Using Part Proposal Networks

The study of mouse social behaviors has been increasingly undertaken in neuroscience research. However, automated quantification of mouse behaviors from the videos of interacting mice is still a challenging problem, where object tracking plays a key role in locating mice in their living spaces. Artificial markers are often applied for multiple mice tracking, which are intrusive and consequently interfere with the movements of mice in a dynamic environment. In this article, we propose a novel method to continuously track several mice and individual parts without requiring any specific tagging. First, we propose an efficient and robust deep-learning-based mouse part detection scheme to generate part candidates. Subsequently, we propose a novel Bayesian-inference integer linear programming (BILP) model that jointly assigns the part candidates to individual targets with necessary geometric constraints while establishing pair-wise association between the detected parts. There is no publicly available dataset in the research community that provides a quantitative test bed for part detection and tracking of multiple mice, and we here introduce a new challenging Multi-Mice PartsTrack dataset that is made of complex behaviors. Finally, we evaluate our proposed approach against several baselines on our new datasets, where the results show that our method outperforms the other state-of-the-art approaches in terms of accuracy. We also demonstrate the generalization ability of the proposed approach on tracking zebra and locust.

A Robust Visual System for Looming Cue Detection Against Translating Motion

Collision detection is critical for autonomous vehicles or robots to serve human society safely. Detecting looming objects robustly and timely plays an important role in collision avoidance systems. The locust lobula giant movement detector (LGMD1) is specifically selective to looming objects which are on a direct collision course. However, the existing LGMD1 models cannot distinguish a looming object from a near and fast translatory moving object, because the latter can evoke a large amount of excitation that can lead to false LGMD1 spikes. This article presents a new visual neural system model (LGMD1) that applies a neural competition mechanism within a framework of separated ON and OFF pathways to shut off the translating response. The competition-based approach responds vigorously to monotonous ON/OFF responses resulting from a looming object. However, it does not respond to paired ON-OFF responses that result from a translating object, thereby enhancing collision selectivity. Moreover, a complementary denoising mechanism ensures reliable collision detection. To verify the effectiveness of the model, we have conducted systematic comparative experiments on synthetic and real datasets. The results show that our method exhibits more accurate discrimination between looming and translational events-the looming motion can be correctly detected. It also demonstrates that the proposed model is more robust than comparative models.

Attention and Prediction-Guided Motion Detection for Low-Contrast Small Moving Targets

Small target motion detection within complex natural environments is an extremely challenging task for autonomous robots. Surprisingly, the visual systems of insects have evolved to be highly efficient in detecting mates and tracking prey, even though targets occupy as small as a few degrees of their visual fields. The excellent sensitivity to small target motion relies on a class of specialized neurons, called small target motion detectors (STMDs). However, existing STMD-based models are heavily dependent on visual contrast and perform poorly in complex natural environments, where small targets generally exhibit extremely low contrast against neighboring backgrounds. In this article, we develop an attention-and-prediction-guided visual system to overcome this limitation. The developed visual system comprises three main subsystems, namely: 1) an attention module; 2) an STMD-based neural network; and 3) a prediction module. The attention module searches for potential small targets in the predicted areas of the input image and enhances their contrast against a complex background. The STMD-based neural network receives the contrast-enhanced image and discriminates small moving targets from background false positives. The prediction module foresees future positions of the detected targets and generates a prediction map for the attention module. The three subsystems are connected in a recurrent architecture, allowing information to be processed sequentially to activate specific areas for small target detection. Extensive experiments on synthetic and real-world datasets demonstrate the effectiveness and superiority of the proposed visual system for detecting small, low-contrast moving targets against complex natural environments.

Motion perception based on ON/OFF channels: A survey

Motion perception is an essential ability for animals and artificially intelligent systems interacting effectively, safely with surrounding objects and environments. Biological visual systems, that have naturally evolved over hundreds-million years, are quite efficient and robust for motion perception, whereas artificial vision systems are far from such capability. This paper argues that the gap can be significantly reduced by formulation of ON/OFF channels in motion perception models encoding luminance increment (ON) and decrement (OFF) responses within receptive field, separately. Such signal-bifurcating structure has been found in neural systems of many animal species articulating early motion is split and processed in segregated pathways. However, the corresponding biological substrates, and the necessity for artificial vision systems have never been elucidated together, leaving concerns on uniqueness and advantages of ON/OFF channels upon building dynamic vision systems to address real world challenges. This paper highlights the importance of ON/OFF channels in motion perception through surveying current progress covering both neuroscience and computationally modelling works with applications. Compared to related literature, this paper for the first time provides insights into implementation of different selectivity to directional motion of looming, translating, and small-sized target movement based on ON/OFF channels in keeping with soundness and robustness of biological principles. Existing challenges and future trends of such bio-plausible computational structure for visual perception in connection with hotspots of machine learning, advanced vision sensors like event-driven camera finally are discussed.

Enhancing LGMD's Looming Selectivity for UAV With Spatial-Temporal Distributed Presynaptic Connections

Collision detection is one of the most challenging tasks for unmanned aerial vehicles (UAVs). This is especially true for small or micro-UAVs due to their limited computational power. In nature, flying insects with compact and simple visual systems demonstrate their remarkable ability to navigate and avoid collision in complex environments. A good example of this is provided by locusts. They can avoid collisions in a dense swarm through the activity of a motion-based visual neuron called the Lobula giant movement detector (LGMD). The defining feature of the LGMD neuron is its preference for looming. As a flying insect's visual neuron, LGMD is considered to be an ideal basis for building UAV's collision detecting system. However, existing LGMD models cannot distinguish looming clearly from other visual cues, such as complex background movements caused by UAV agile flights. To address this issue, we proposed a new model implementing distributed spatial-temporal synaptic interactions, which is inspired by recent findings in locusts' synaptic morphology. We first introduced the locally distributed excitation to enhance the excitation caused by visual motion with preferred velocities. Then, radially extending temporal latency for inhibition is incorporated to compete with the distributed excitation and selectively suppress the nonpreferred visual motions. This spatial-temporal competition between excitation and inhibition in our model is, therefore, tuned to preferred image angular velocity representing looming rather than background movements with these distributed synaptic interactions. Systematic experiments have been conducted to verify the performance of the proposed model for UAV agile flights. The results have demonstrated that this new model enhances the looming selectivity in complex flying scenes considerably and has the potential to be implemented on embedded collision detection systems for small or micro-UAVs.

A Time-Delay Feedback Neural Network for Discriminating Small, Fast-Moving Targets in Complex Dynamic Environments

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 article, 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 that it shows a 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.

Weighted Matrix Decomposition for Small Surface Defect Detection

Detecting small defects against a complex surface is highly challenging but crucial to ensure product quality in industry sectors. However, in the detection performance of existing methods, there remains a huge gap in the localization and segmentation of small defects with limited sizes and extremely weak feature representation. To address the above issue, this paper presents a weighted matrix decomposition model (WMD) for small defect detection against a complex surface. Firstly, a weighted matrix is constructed based on texture characteristics of RGB channels in the defect image, which aims to improve contrast between defects and the background. Based on the sparse and low-rank characteristics of small defects, the weighted matrix is then decomposed into low-rank and sparse matrices corresponding to the redundant background and defect areas, respectively. Finally, an automatic threshold segmentation method is used to obtain the optimal threshold and accurately segment the defect areas and their edges in the sparse matrix. The experimental results show that the proposed model outperforms state-of-the-art methods under various quantitative evaluation metrics and has broad industrial application prospects.

Mathematical study of neural feedback roles in small target motion detection

Building an efficient and reliable small target motion detection visual system is challenging for artificial intelligence robotics because a small target only occupies few pixels and hardly displays visual features in images. Biological visual systems that have evolved over millions of years could be ideal templates for designing artificial visual systems. Insects benefit from a class of specialized neurons, called small target motion detectors (STMDs), which endow them with an excellent ability to detect small moving targets against a cluttered dynamic environment. Some bio-inspired models featured in feed-forward information processing architectures have been proposed to imitate the functions of the STMD neurons. However, feedback, a crucial mechanism for visual system regulation, has not been investigated deeply in the STMD-based neural circuits and its roles in small target motion detection remain unclear. In this paper, we propose a time-delay feedback STMD model for small target motion detection in complex backgrounds. The main contributions of this study are as follows. First, a feedback pathway is designed by transmitting information from output-layer neurons to lower-layer interneurons in the STMD pathway and the role of the feedback is analyzed from the view of mathematical analysis. Second, to estimate the feedback constant, the existence and uniqueness of solutions for nonlinear dynamical systems formed by feedback loop are analyzed via Schauder's fixed point theorem and contraction mapping theorem. Finally, an iterative algorithm is designed to solve the nonlinear problem and the performance of the proposed model is tested by experiments. Experimental results demonstrate that the feedback is able to weaken background false positives while maintaining a minor effect on small targets. It outperforms existing STMD-based models regarding the accuracy of fast-moving small target detection in visual clutter. The proposed feedback approach could inspire the relevant modeling of robust motion perception robotics visual systems.

Detection of Small Aerial Object Using Random Projection Feature With Region Clustering

Small aerial object detection plays an important role in numerous computer vision tasks, including remote sensing, early warning systems, and visual tracking. Despite existing moving object detection techniques that can achieve reasonable results in normal size objects, they fail to distinguish the small objects from the dynamic background. To cope with this issue, a novel method is proposed for accurate small aerial object detection under different situations. Initially, the block segmentation is introduced for reducing frame information redundancy. Meanwhile, a random projection feature (RPF) is proposed for characterizing blocks into feature vectors. Subsequently, a moving direction estimation based on feature vectors is presented to measure the motions of blocks and filter out the major directions. Finally, variable search region clustering (VSRC), together with the color feature difference, is designed for extracting pixelwise targets from the remaining moving direction blocks. The comprehensive experiments demonstrate that our approach outperforms the level of state-of-the-art methods upon the integrity of small aerial objects, especially on the dynamic background and scale variation targets.

A Looming Spatial Localization Neural Network Inspired by MLG1 Neurons in the Crab Neohelice

Similar to most visual animals, the crab Neohelice granulata relies predominantly on visual information to escape from predators, to track prey and for selecting mates. It, therefore, needs specialized neurons to process visual information and determine the spatial location of looming objects. In the crab Neohelice granulata, the Monostratified Lobula Giant type1 (MLG1) neurons have been found to manifest looming sensitivity with finely tuned capabilities of encoding spatial location information. MLG1s neuronal ensemble can not only perceive the location of a looming stimulus, but are also thought to be able to influence the direction of movement continuously, for example, escaping from a threatening, looming target in relation to its position. Such specific characteristics make the MLG1s unique compared to normal looming detection neurons in invertebrates which can not localize spatial looming. Modeling the MLG1s ensemble is not only critical for elucidating the mechanisms underlying the functionality of such neural circuits, but also important for developing new autonomous, efficient, directionally reactive collision avoidance systems for robots and vehicles. However, little computational modeling has been done for implementing looming spatial localization analogous to the specific functionality of MLG1s ensemble. To bridge this gap, we propose a model of MLG1s and their pre-synaptic visual neural network to detect the spatial location of looming objects. The model consists of 16 homogeneous sectors arranged in a circular field inspired by the natural arrangement of 16 MLG1s' receptive fields to encode and convey spatial information concerning looming objects with dynamic expanding edges in different locations of the visual field. Responses of the proposed model to systematic real-world visual stimuli match many of the biological characteristics of MLG1 neurons. The systematic experiments demonstrate that our proposed MLG1s model works effectively and robustly to perceive and localize looming information, which could be a promising candidate for intelligent machines interacting within dynamic environments free of collision. This study also sheds light upon a new type of neuromorphic visual sensor strategy that can extract looming objects with locational information in a quick and reliable manner.

Nonlinear, neuronal adaptation in insect vision models improves target discrimination within repetitively moving backgrounds

Neurons which respond selectively to small moving targets, even against a cluttered background, have been identified in several insect species. To investigate what underlies these robust and highly selective responses, researchers have probed the neuronal circuitry in target-detecting, visual pathways. Observations in flies reveal nonlinear adaptation over time, composed of a fast onset and gradual decay. This adaptive processing is seen in both of the independent, parallel pathways encoding either luminance increments (ON channel) or decrements (OFF channel). The functional significance of this adaptive phenomenon has not been determined from physiological studies, though the asymmetrical time course suggests a role in suppressing responses to repetitive stimuli. We tested this possibility by comparing an implementation of fast adaptation against alternatives, using a model of insect 'elementary small target motion detectors'. We conducted target-detecting simulations on various natural backgrounds, that were shifted via several movement profiles (and target velocities). Using performance metrics, we confirmed that the fast adaptation observed in neuronal systems enhances target detection against a repetitively moving background. Such background movement would be encountered via natural ego-motion as the insect travels through the world. These findings show that this form of nonlinear, fast-adaptation (suitably implementable via cellular biophysics) plays a role analogous to background subtraction techniques in conventional computer vision.

Cascaded Correlation Refinement for Robust Deep Tracking

Recent deep trackers have shown superior performance in visual tracking. In this article, we propose a cascaded correlation refinement approach to facilitate the robustness of deep tracking. The core idea is to address accurate target localization and reliable model update in a collaborative way. To this end, our approach cascades multiple stages of correlation refinement to progressively refine target localization. Thus, the localized object could be used to learn an accurate on-the-fly model for improving the reliability of model update. Meanwhile, we introduce an explicit measure to identify the tracking failure and then leverage a simple yet effective look-back scheme to adaptively incorporate the initial model and on-the-fly model to update the tracking model. As a result, the tracking model can be used to localize the target more accurately. Extensive experiments on OTB2013, OTB2015, VOT2016, VOT2018, UAV123, and GOT-10k demonstrate that the proposed tracker achieves the best robustness against the state of the arts.

A Method for Detection of Small Moving Objects in UAV Videos

Detection of small moving objects is an important research area with applications including monitoring of flying insects, studying their foraging behavior, using insect pollinators to monitor flowering and pollination of crops, surveillance of honeybee colonies, and tracking movement of honeybees. However, due to the lack of distinctive shape and textural details on small objects, direct application of modern object detection methods based on convolutional neural networks (CNNs) shows considerably lower performance. In this paper we propose a method for the detection of small moving objects in videos recorded using unmanned aerial vehicles equipped with standard video cameras. The main steps of the proposed method are video stabilization, background estimation and subtraction, frame segmentation using a CNN, and thresholding the segmented frame. However, for training a CNN it is required that a large labeled dataset is available. Manual labelling of small moving objects in videos is very difficult and time consuming, and such labeled datasets do not exist at the moment. To circumvent this problem, we propose training a CNN using synthetic videos generated by adding small blob-like objects to video sequences with real-world backgrounds. The experimental results on detection of flying honeybees show that by using a combination of classical computer vision techniques and CNNs, as well as synthetic training sets, the proposed approach overcomes the problems associated with direct application of CNNs to the given problem and achieves an average F1-score of 0.86 in tests on real-world videos.