Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications. To address this challenge, this paper proposes a real-time, hybrid neuromorphic framework for object tracking and classification using event-based cameras that possess properties such as low-power consumption (5-14 mW) and high dynamic range (120 dB). Nonetheless, unlike traditional approaches of using event-by-event processing, this work uses a mixed frame and event approach to get energy savings with high performance. Using a frame-based region proposal method based on the density of foreground events, a hardware-friendly object tracking scheme is implemented using the apparent object velocity while tackling occlusion scenarios. The object track input is converted back to spikes for TrueNorth classification via the energy-efficient deep network (EEDN) pipeline. Using originally collected datasets, we train the TrueNorth model on the hardware track outputs, instead of using ground truth object locations as commonly done, and demonstrate the ability of our system to handle practical surveillance scenarios. As an optional paradigm, to exploit the low latency and asynchronous nature of neuromorphic vision sensors (NVS), we also propose a continuous-time tracker with C++ implementation where each event is processed individually. Thereby, we extensively compare the proposed methodologies to state-of-the-art event-based and frame-based methods for object tracking and classification, and demonstrate the use case of our neuromorphic approach for real-time and embedded applications without sacrificing performance. Finally, we also showcase the efficacy of the proposed system to a standard RGB camera setup when evaluated over several hours of traffic recordings.
Although short-term fully occlusion happens rare in visual object tracking, most trackers will fail under these circumstances. However, humans can still catch up the target by anticipating the trajectory of the target even the target is invisible. Recent psychology also has shown that humans build the mental image of the future. Inspired by that, we present a HAllucinating Features to Track (HAFT) model that enables to forecast the visual feature embedding of future frames. The anticipated future frames focus on the movement of the target while hallucinating the occluded part of the target. Jointly tracking on the hallucinated features and the real features improves the robustness of the tracker even when the target is highly occluded. Through extensive experimental evaluations, we achieve promising results on multiple datasets: OTB100, VOT2018, LaSOT, TrackingNet, and UAV123.
Tracking a car or a person in a city is crucial for urban safety management. How can we complete the task with minimal number of spatiotemporal searches from massive camera records? This paper proposes a strategy named IHMs (Intermediate Searching at Heuristic Moments): each step we figure out which moment is the best to search according to a heuristic indicator, then at that moment search locations one by one in descending order of predicted appearing probabilities, until a search hits; iterate this step until we get the object's current location. Five searching strategies are compared in experiments, and IHMs is validated to be most efficient, which can save up to 1/3 total costs. This result provides an evidence that "searching at intermediate moments can save cost".
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to obtain accurate detections due to heavy occlusions and high crowd density. In this paper, we propose a new MOT paradigm, tracking-by-counting, tailored for crowded scenes. Using crowd density maps, we jointly model detection, counting, and tracking of multiple targets as a network flow program, which simultaneously finds the global optimal detections and trajectories of multiple targets over the whole video. This is in contrast to prior MOT methods that either ignore the crowd density and thus are prone to errors in crowded scenes, or rely on a suboptimal two-step process using heuristic density-aware point-tracks for matching targets.Our approach yields promising results on public benchmarks of various domains including people tracking, cell tracking, and fish tracking.
Siamese trackers turn tracking into similarity estimation between a template and the candidate regions in the frame. Mathematically, one of the key ingredients of success of the similarity function is translation equivariance. Non-translation-equivariant architectures induce a positional bias during training, so the location of the target will be hard to recover from the feature space. In real life scenarios, objects undergoe various transformations other than translation, such as rotation or scaling. Unless the model has an internal mechanism to handle them, the similarity may degrade. In this paper, we focus on scaling and we aim to equip the Siamese network with additional built-in scale equivariance to capture the natural variations of the target a priori. We develop the theory for scale-equivariant Siamese trackers, and provide a simple recipe for how to make a wide range of existing trackers scale-equivariant. We present SE-SiamFC, a scale-equivariant variant of SiamFC built according to the recipe. We conduct experiments on OTB and VOT benchmarks and on the synthetically generated T-MNIST and S-MNIST datasets. We demonstrate that a built-in additional scale equivariance is useful for visual object tracking.
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering. A potential drawback of using pseudo labels is that errors may accumulate and it is challenging to estimate the number of pseudo IDs. We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels. The goal is to construct a self-supervised pretext task that matches the person re-ID objective. Inspired by the \emph{data association} concept in multi-object tracking, we propose the \textbf{Cyc}le \textbf{As}sociation (\textbf{CycAs}) task: after performing data association between a pair of video frames forward and then backward, a pedestrian instance is supposed to be associated to itself. To fulfill this goal, the model must learn a meaningful representation that can well describe correspondences between instances in frame pairs. We adapt the discrete association process to a differentiable form, such that end-to-end training becomes feasible. Experiments are conducted in two aspects: We first compare our method with existing unsupervised re-ID methods on seven benchmarks and demonstrate CycAs' superiority. Then, to further validate the practical value of CycAs in real-world applications, we perform training on self-collected videos and report promising performance on standard test sets.
Assigning consistent temporal identifiers to multiple moving objects in a video sequence is a challenging problem. A solution to that problem would have immediate ramifications in multiple object tracking and segmentation problems. We propose a strategy that treats the temporal identification task as a spatio-temporal clustering problem. We propose an unsupervised learning approach using a convolutional and fully connected autoencoder, which we call deep heterogeneous autoencoder, to learn discriminative features from segmentation masks and detection bounding boxes. We extract masks and their corresponding bounding boxes from a pretrained instance segmentation network and train the autoencoders jointly using task-dependent uncertainty weights to generate common latent features. We then construct constraints graphs that encourage associations among objects that satisfy a set of known temporal conditions. The feature vectors and the constraints graphs are then provided to the kmeans clustering algorithm to separate the corresponding data points in the latent space. We evaluate the performance of our method using challenging synthetic and real-world multiple-object video datasets. Our results show that our technique outperforms several state-of-the-art methods.
Recently, some correlation filter based trackers with detection proposals have achieved state-of-the-art tracking results. However, a large number of redundant proposals given by the proposal generator may degrade the performance and speed of these trackers. In this paper, we propose an adaptive proposal selection algorithm which can generate a small number of high-quality proposals to handle the problem of scale variations for visual object tracking. Specifically, we firstly utilize the color histograms in the HSV color space to represent the instances (i.e., the initial target in the first frame and the predicted target in the previous frame) and proposals. Then, an adaptive strategy based on the color similarity is formulated to select high-quality proposals. We further integrate the proposed adaptive proposal selection algorithm with coarse-to-fine deep features to validate the generalization and efficiency of the proposed tracker. Experiments on two benchmark datasets demonstrate that the proposed algorithm performs favorably against several state-of-the-art trackers.
Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking, significantly much more research effort has been made in segmentation than tracking. In this paper, we introduce "tracking-by-detection" into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. Notably, our method is entirely online and thus suitable for one-shot learning, and our end-to-end trainable model allows multiple object segmentation in one forward pass. We achieve new state-of-the-art performance on the DAVIS benchmark without complicated bells and whistles in both speed and accuracy, with a speed of 0.14 second per frame and J&F measure of 75.9% respectively.
There is an increased interest in the use of Unmanned Aerial Vehicles (UAVs) for agriculture, military, disaster management and aerial photography around the world. UAVs are scalable, flexible and are useful in various environments where direct human intervention is difficult. In general, the use of UAVs with cameras mounted to them has increased in number due to their wide range of applications in real life scenarios. With the advent of deep learning models in computer vision many models have shown great success in visual tasks. But most of evaluation models are done on high end CPUs and GPUs. One of major challenges in using UAVs for Visual Assistance tasks in real time is managing the memory usage and power consumption of the these tasks which are computationally intensive and are difficult to be performed on low end processor board of the UAV. This projects describes a novel method to optimize the general image processing tasks like object tracking and object detection for UAV hardware in real time scenarios without affecting the flight time and not tampering the latency and accuracy of these models.
With the recent advances in the object detection research field, tracking-by-detection has become the leading paradigm adopted by multi-object tracking algorithms. By extracting different features from detected objects, those algorithms can estimate the objects' similarities and association patterns along successive frames. However, since similarity functions applied by tracking algorithms are handcrafted, it is difficult to employ them in new contexts. In this study, it is investigated the use of artificial neural networks to learning a similarity function that can be used among detections. During training, the networks were introduced to correct and incorrect association patterns, sampled from a pedestrian tracking data set. For such, different motion and appearance features combinations have been explored. Finally, a trained network has been inserted into a multiple-object tracking framework, which has been assessed on the MOT Challenge benchmark. Throughout the experiments, the proposed tracker matched the results obtained by state-of-the-art methods, it has run 58\% faster than a recent and similar method, used as baseline.
Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably improve the object detection performance and also provide good appearance features for cross-frame association, the framework is not completely end-to-end, and therefore the computation is huge while the performance is limited. To address the problem, we present a completely end-to-end approach that takes image-sequence/video as input and outputs directly the located and tracked objects of learned types. Specifically, with our introduced multi-object representation strategy, a global response map can be accurately generated over frames, from which the trajectory of each tracked object can be easily picked up, just like how a detector inputs an image and outputs the bounding boxes of each detected object. The proposed model is fast and accurate. Experimental results based on the MOT16 and MOT17 benchmarks show that our proposed on-line tracker achieved state-of-the-art performance on several tracking metrics.
Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology that takes advantage of other visual trackers, offline and online. A compact student model is trained via the marriage of knowledge distillation and reinforcement learning. The first allows to transfer and compress tracking knowledge of other trackers. The second enables the learning of evaluation measures which are then exploited online. After learning, the student can be ultimately used to build (i) a very fast single-shot tracker, (ii) a tracker with a simple and effective online adaptation mechanism, (iii) a tracker that performs fusion of other trackers. Extensive validation shows that the proposed algorithms compete with real-time state-of-the-art trackers.
We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement. However, it remains challenging for refining MOTS results, which could be attributed to that appearance features are not adapted to target videos and it is also difficult to find proper thresholds to discriminate them. To tackle this issue, we propose a self-supervised refining MOTS (i.e., ReMOTS) framework. ReMOTS mainly takes four steps to refine MOTS results from the data association perspective. (1) Training the appearance encoder using predicted masks. (2) Associating observations across adjacent frames to form short-term tracklets. (3) Training the appearance encoder using short-term tracklets as reliable pseudo labels. (4) Merging short-term tracklets to long-term tracklets utilizing adopted appearance features and thresholds that are automatically obtained from statistical information. Using ReMOTS, we reached the $1^{st}$ place on CVPR 2020 MOTS Challenge 1, with an sMOTSA score of $69.9$.
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt convolutions for feature extraction. However, as affected by the inherent receptive field, convolution based feature extraction inevitably mixes up the foreground features and the background features, resulting in ambiguities in the subsequent instance association. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. Our method generates a new tracking-by-points paradigm where discriminative instance embeddings are learned from randomly selected points rather than images. Furthermore, multiple informative data modalities are converted into point-wise representations to enrich point-wise features. The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5.4% higher MOTSA and 18 times faster over MOTSFusion) with the near real-time speed (22 FPS). Evaluations across three datasets demonstrate both the effectiveness and efficiency of our method. Moreover, based on the observation that current MOTS datasets lack crowded scenes, we build a more challenging MOTS dataset named APOLLO MOTS with higher instance density. Both APOLLO MOTS and our codes are publicly available at https://github.com/detectRecog/PointTrack.
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework. To begin with, PointTrack adopts an efficient one-stage framework for instance segmentation, and learns instance embeddings by converting compact image representations to un-ordered 2D point cloud. Compared with PointTrack, our proposed PointTrack++ offers three major improvements. Firstly, in the instance segmentation stage, we adopt a semantic segmentation decoder trained with focal loss to improve the instance selection quality. Secondly, to further boost the segmentation performance, we propose a data augmentation strategy by copy-and-paste instances into training images. Finally, we introduce a better training strategy in the instance association stage to improve the distinguishability of learned instance embeddings. The resulting framework achieves the state-of-the-art performance on the 5th BMTT MOTChallenge.
Visual object tracking (VOT) is an essential component for many applications, such as autonomous driving or assistive robotics. However, recent works tend to develop accurate systems based on more computationally expensive feature extractors for better instance matching. In contrast, this work addresses the importance of motion prediction in VOT. We use an off-the-shelf object detector to obtain instance bounding boxes. Then, a combination of camera motion decouple and Kalman filter is used for state estimation. Although our baseline system is a straightforward combination of standard methods, we obtain state-of-the-art results. Our method establishes new state-of-the-art performance on VOT (VOT-2016 and VOT-2018). Our proposed method improves the EAO on VOT-2016 from 0.472 of prior art to 0.505, from 0.410 to 0.431 on VOT-2018. To show the generalizability, we also test our method on video object segmentation (VOS: DAVIS-2016 and DAVIS-2017) and observe consistent improvement.
Tracking and localizing objects is a central problem in computer-assisted surgery. Optical coherence tomography (OCT) can be employed as an optical tracking system, due to its high spatial and temporal resolution. Recently, 3D convolutional neural networks (CNNs) have shown promising performance for pose estimation of a marker object using single volumetric OCT images. While this approach relied on spatial information only, OCT allows for a temporal stream of OCT image volumes capturing the motion of an object at high volumes rates. In this work, we systematically extend 3D CNNs to 4D spatio-temporal CNNs to evaluate the impact of additional temporal information for marker object tracking. Across various architectures, our results demonstrate that using a stream of OCT volumes and employing 4D spatio-temporal convolutions leads to a 30% lower mean absolute error compared to single volume processing with 3D CNNs.
Most modern multi-object tracking (MOT) systems follow the tracking-by-detection paradigm. It first localizes the objects of interest, then extracting their individual appearance features to make data association. The individual features, however, are susceptible to the negative effects as occlusions, illumination variations and inaccurate detections, thus resulting in the mismatch in the association inference. In this work, we propose to handle this problem via making full use of the neighboring information. Our motivations derive from the observations that people tend to move in a group. As such, when an individual target's appearance is seriously changed, we can still identify it with the help of its neighbors. To this end, we first utilize the spatio-temporal relations produced by the tracking self to efficiently select suitable neighbors for the targets. Subsequently, we construct neighbor graph of the target and neighbors then employ the graph convolution networks (GCN) to learn the graph features. To the best of our knowledge, it is the first time to exploit neighbor cues via GCN in MOT. Finally, we test our approach on the MOT benchmarks and achieve state-of-the-art performance in online tracking.
In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations - from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover, quantisation of weights positively affects the network training by decreasing overfitting.