Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed. However, the backbone networks used in Siamese trackers are relatively shallow, such as AlexNet [18], which does not fully take advantage of the capability of modern deep neural networks. In this paper, we investigate how to leverage deeper and wider convolutional neural networks to enhance tracking robustness and accuracy. We observe that direct replacement of backbones with existing powerful architectures, such as ResNet [14] and Inception [33], does not bring improvements. The main reasons are that 1)large increases in the receptive field of neurons lead to reduced feature discriminability and localization precision; and 2) the network padding for convolutions induces a positional bias in learning. To address these issues, we propose new residual modules to eliminate the negative impact of padding, and further design new architectures using these modules with controlled receptive field size and network stride. The designed architectures are lightweight and guarantee real-time tracking speed when applied to SiamFC [2] and SiamRPN [20]. Experiments show that solely due to the proposed network architectures, our SiamFC+ and SiamRPN+ obtain up to 9.8%/5.7% (AUC), 23.3%/8.8% (EAO) and 24.4%/25.0% (EAO) relative improvements over the original versions [2, 20] on the OTB-15, VOT-16 and VOT-17 datasets, respectively.
Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they cannot take advantage of feature from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResNet-driven Siamese tracker with significant performance gain. Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size. We conduct extensive ablation studies to demonstrate the effectiveness of the proposed tracker, which obtains currently the best results on four large tracking benchmarks, including OTB2015, VOT2018, UAV123, and LaSOT. Our model will be released to facilitate further studies based on this problem.
A saliency guided hierarchical visual tracking (SHT) algorithm containing global and local search phases is proposed in this paper. In global search, a top-down saliency model is novelly developed to handle abrupt motion and appearance variation problems. Nineteen feature maps are extracted first and combined with online learnt weights to produce the final saliency map and estimated target locations. After the evaluation of integration mechanism, the optimum candidate patch is passed to the local search. In local search, a superpixel based HSV histogram matching is performed jointly with an L2-RLS tracker to take both color distribution and holistic appearance feature of the object into consideration. Furthermore, a linear refinement search process with fast iterative solver is implemented to attenuate the possible negative influence of dominant particles. Both qualitative and quantitative experiments are conducted on a series of challenging image sequences. The superior performance of the proposed method over other state-of-the-art algorithms is demonstrated by comparative study.
In this paper, a robust visual tracking approach via mixed model based convolutional neural networks (SDT) is developed. In order to handle abrupt or fast motion, a prior map is generated to facilitate the localization of region of interest (ROI) before the deep tracker is performed. A top-down saliency model with nineteen shallow cues are employed to construct the prior map with online learnt combination weights. Moreover, apart from a holistic deep learner, four local networks are also trained to learn different components of the target. The generated four local heat maps will facilitate to rectify the holistic map by eliminating the distracters to avoid drifting. Furthermore, to guarantee the instance for online update of high quality, a prioritised update strategy is implemented by casting the problem into a label noise problem. The selection probability is designed by considering both confidence values and bio-inspired memory for temporal information integration. Experiments are conducted qualitatively and quantitatively on a set of challenging image sequences. Comparative study demonstrates that the proposed algorithm outperforms other state-of-the-art methods.
Region proposal networks (RPN) have been recently combined with the Siamese network for tracking, and shown excellent accuracy with high efficiency. Nevertheless, previously proposed one-stage Siamese-RPN trackers degenerate in presence of similar distractors and large scale variation. Addressing these issues, we propose a multi-stage tracking framework, Siamese Cascaded RPN (C-RPN), which consists of a sequence of RPNs cascaded from deep high-level to shallow low-level layers in a Siamese network. Compared to previous solutions, C-RPN has several advantages: (1) Each RPN is trained using the outputs of RPN in the previous stage. Such process stimulates hard negative sampling, resulting in more balanced training samples. Consequently, the RPNs are sequentially more discriminative in distinguishing difficult background (i.e., similar distractors). (2) Multi-level features are fully leveraged through a novel feature transfer block (FTB) for each RPN, further improving the discriminability of C-RPN using both high-level semantic and low-level spatial information. (3) With multiple steps of regressions, C-RPN progressively refines the location and shape of the target in each RPN with adjusted anchor boxes in the previous stage, which makes localization more accurate. C-RPN is trained end-to-end with the multi-task loss function. In inference, C-RPN is deployed as it is, without any temporal adaption, for real-time tracking. In extensive experiments on OTB-2013, OTB-2015, VOT-2016, VOT-2017, LaSOT and TrackingNet, C-RPN consistently achieves state-of-the-art results and runs in real-time.
Visual Tracking is a complex problem due to unconstrained appearance variations and dynamic environment. Extraction of complementary information from the object environment via multiple features and adaption to the target's appearance variations are the key problems of this work. To this end, we propose a robust object tracking framework based on Unified Graph Fusion (UGF) of multi-cue to adapt to the object's appearance. The proposed cross-diffusion of sparse and dense features not only suppresses the individual feature deficiencies but also extracts the complementary information from multi-cue. This iterative process builds robust unified features which are invariant to object deformations, fast motion, and occlusion. Robustness of the unified feature also enables the random forest classifier to precisely distinguish the foreground from the background, adding resilience to background clutter. In addition, we present a novel kernel-based adaptation strategy using outlier detection and a transductive reliability metric.
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask.
This paper presents a semi-supervised learning framework to train a keypoint detector using multiview image streams given the limited labeled data (typically $<$4\%). We leverage the complementary relationship between multiview geometry and visual tracking to provide three types of supervisionary signals to utilize the unlabeled data: (1) keypoint detection in one view can be supervised by other views via the epipolar geometry; (2) a keypoint moves smoothly over time where its optical flow can be used to temporally supervise consecutive image frames to each other; (3) visible keypoint in one view is likely to be visible in the adjacent view. We integrate these three signals in a differentiable fashion to design a new end-to-end neural network composed of three pathways. This design allows us to extensively use the unlabeled data to train the keypoint detector. We show that our approach outperforms existing detectors including DeepLabCut tailored to the keypoint detection of non-human species such as monkeys, dogs, and mice.
This paper investigates how to perform robust visual tracking in adverse and challenging conditions using complementary visual and thermal infrared data (RGBT tracking). We propose a novel deep network architecture called qualityaware Feature Aggregation Network (FANet) for robust RGBT tracking. Unlike existing RGBT trackers, our FANet aggregates hierarchical deep features within each modality to handle the challenge of significant appearance changes caused by deformation, low illumination, background clutter and occlusion. In particular, we employ the operations of max pooling to transform these hierarchical and multi-resolution features into uniform space with the same resolution, and use 1x1 convolution operation to compress feature dimensions to achieve more effective hierarchical feature aggregation. To model the interactions between RGB and thermal modalities, we elaborately design an adaptive aggregation subnetwork to integrate features from different modalities based on their reliabilities and thus are able to alleviate noise effects introduced by low-quality sources. The whole FANet is trained in an end-to-end manner. Extensive experiments on large-scale benchmark datasets demonstrate the high-accurate performance against other state-of-the-art RGBT tracking methods.
For visual tracking, most of the traditional correlation filters (CF) based methods suffer from the bottleneck of feature redundancy and lack of motion information. In this paper, we design a novel tracking framework, called multi-hierarchical independent correlation filters (MHIT). The framework consists of motion estimation module, hierarchical features selection, independent CF online learning, and adaptive multi-branch CF fusion. Specifically, the motion estimation module is introduced to capture motion information, which effectively alleviates the object partial occlusion in the temporal video. The multi-hierarchical deep features of CNN representing different semantic information can be fully excavated to track multi-scale objects. To better overcome the deep feature redundancy, each hierarchical features are independently fed into a single branch to implement the online learning of parameters. Finally, an adaptive weight scheme is integrated into the framework to fuse these independent multi-branch CFs for the better and more robust visual object tracking. Extensive experiments on OTB and VOT datasets show that the proposed MHIT tracker can significantly improve the tracking performance. Especially, it obtains a 20.1% relative performance gain compared to the top trackers on the VOT2017 challenge, and also achieves new state-of-the-art performance on the VOT2018 challenge.
It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations. To cope with this problem, a promising solution is to integrate the temporal consistency across consecutive frames and multiple feature cues in a unified model. Motivated by this idea, we propose a novel correlation filter-based tracker in this work, in which the temporal relatedness is reconciled under a multi-task learning framework and the multiple feature cues are modeled using a multi-view learning approach. We demonstrate the resulting regression model can be efficiently learned by exploiting the structure of blockwise diagonal matrix. A fast blockwise diagonal matrix inversion algorithm is developed thereafter for efficient online tracking. Meanwhile, we incorporate an adaptive scale estimation mechanism to strengthen the stability of scale variation tracking. We implement our tracker using two types of features and test it on two benchmark datasets. Experimental results demonstrate the superiority of our proposed approach when compared with other state-of-the-art trackers. project homepage http://bmal.hust.edu.cn/project/KMF2JMTtracking.html
While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring high-level knowledge about the object. We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating target-specific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale TrackingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https://github.com/visionml/pytracking.
To study the preference of infants for contingency of movements and familiarity of faces during self-recognition task, we built, as an accurate and instantaneous imitator, a real-time face- swapper for videos. We present a non-constraint face-swapper based on 3D visual tracking that achieves real-time performance through parallel computing. Our imitator system is par- ticularly suited for experiments involving children with Autistic Spectrum Disorder who are often strongly disturbed by the constraints of other methods.
Correlation filter has been proven to be an effective tool for a number of approaches in visual tracking, particularly for seeking a good balance between tracking accuracy and speed. However, correlation filter based models are susceptible to wrong updates stemming from inaccurate tracking results. To date, little effort has been devoted towards handling the correlation filter update problem. In this paper, we propose a novel approach to address the correlation filter update problem. In our approach, we update and maintain multiple correlation filter models in parallel, and we use deep reinforcement learning for the selection of an optimal correlation filter model among them. To facilitate the decision process in an efficient manner, we propose a decision-net to deal target appearance modeling, which is trained through hundreds of challenging videos using proximal policy optimization and a lightweight learning network. An exhaustive evaluation of the proposed approach on the OTB100 and OTB2013 benchmarks show that the approach is effective enough to achieve the average success rate of 62.3% and the average precision score of 81.2%, both exceeding the performance of traditional correlation filter based trackers.
In recent years, Discriminative Correlation Filter (DCF) based tracking methods have achieved great success in visual tracking. However, the multi-resolution convolutional feature maps trained from other tasks like image classification, cannot be naturally used in the conventional DCF formulation. Furthermore, these high-dimensional feature maps significantly increase the tracking complexity and thus limit the tracking speed. In this paper, we present a deep and shallow feature learning network, namely DSNet, to learn the multi-level same-resolution compressed (MSC) features for efficient online tracking, in an end-to-end offline manner. Specifically, the proposed DSNet compresses multi-level convolutional features to uniform spatial resolution features. The learned MSC features effectively encode both appearance and semantic information of objects in the same-resolution feature maps, thus enabling an elegant combination of the MSC features with any DCF-based methods. Additionally, a channel reliability measurement (CRM) method is presented to further refine the learned MSC features. We demonstrate the effectiveness of the MSC features learned from the proposed DSNet on two DCF tracking frameworks: the basic DCF framework and the continuous convolution operator framework. Extensive experiments show that the learned MSC features have the appealing advantage of allowing the equipped DCF-based tracking methods to perform favorably against the state-of-the-art methods while running at high frame rates.
Correlation filter (CF) based tracking algorithms have demonstrated favorable performance recently. Nevertheless, the top performance trackers always employ complicated optimization methods which constraint their real-time applications. How to accelerate the tracking speed while retaining the tracking accuracy is a significant issue. In this paper, we propose a multi-level CF-based tracking approach named MLCFT which further explores the potential capacity of CF with two-stage detection: primal detection and oriented re-detection. The cascaded detection scheme is simple but competent to prevent model drift and accelerate the speed. An effective fusion method based on relative entropy is introduced to combine the complementary features extracted from deep and shallow layers of convolutional neural networks (CNN). Moreover, a novel online model update strategy is utilized in our tracker, which enhances the tracking performance further. Experimental results demonstrate that our proposed approach outperforms the most state-of-the-art trackers while tracking at speed of exceeded 16 frames per second on challenging benchmarks.
The use of a team of humanoid robots to collaborate in completing a task is an increasingly important field of research. One of the challenges in achieving collaboration, is mutual identification and tracking of the robots. This work presents a real-time vision-based approach to the detection and tracking of robots of known appearance, based on the images captured by a stationary robot. A Histogram of Oriented Gradients descriptor is used to detect the robots and the robot headings are estimated by a multiclass classifier. The tracked robots report their own heading estimate from magnetometer readings. For tracking, a cost function based on position and heading is applied to each of the tracklets, and a globally optimal labeling of the detected robots is found using the Hungarian algorithm. The complete identification and tracking system was tested using two igus Humanoid Open Platform robots on a soccer field. We expect that a similar system can be used with other humanoid robots, such as Nao and DARwIn-OP
Visual tracking is one of the most important application areas of computer vision. At present, most algorithms are mainly implemented on PCs, and it is difficult to ensure real-time performance when applied in the real scenario. In order to improve the tracking speed and reduce the overall power consumption of visual tracking, this paper proposes a real-time visual tracking algorithm based on DSST(Discriminative Scale Space Tracking) approach. We implement a hardware system on Xilinx XC7K325T FPGA platform based on our proposed visual tracking algorithm. Our hardware system can run at more than 153 frames per second. In order to reduce the resource occupation, our system adopts the batch processing method in the feature extraction module. In the filter processing module, the FFT IP core is time-division multiplexed. Therefore, our hardware system utilizes LUTs and storage blocks of 33% and 40%, respectively. Test results show that the proposed visual tracking hardware system has excellent performance.
Video-mapping is the process of coherent video-projection of images, animations or movies on static objects or buildings for shows. This paper focuses on the dynamic video-mapping of the suit of a puppet being moved by its puppeteer on the theater stage. This may allow changing the costume dynamically and simulate light interaction and more. Contrary to common video-mapping, the image warping cannot be done once, offline, before the show. It must be done in real-time, and considering a non-flat projection surface, so that the video-projected suit always maps perfectly the puppet, automatically. Hence, we propose a new visual tracking method of articulated object, for the puppet tracking, exploiting the silhouette of a 3D model of it, in the depth images of a Kinect v2. Then, considering the precise calibration between the latter and the video-projector, that we propose, coherent dynamic video-mapping is made possible as the presented results show.
Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data. Recently, significant efforts have been made to exploit attention schemes to advance computer vision systems. For visual tracking, it is often challenging to track target objects undergoing large appearance changes. Attention maps facilitate visual tracking by selectively paying attention to temporal robust features. Existing tracking-by-detection approaches mainly use additional attention modules to generate feature weights as the classifiers are not equipped with such mechanisms. In this paper, we propose a reciprocative learning algorithm to exploit visual attention for training deep classifiers. The proposed algorithm consists of feed-forward and backward operations to generate attention maps, which serve as regularization terms coupled with the original classification loss function for training. The deep classifier learns to attend to the regions of target objects robust to appearance changes. Extensive experiments on large-scale benchmark datasets show that the proposed attentive tracking method performs favorably against the state-of-the-art approaches.