Target Search Area Research Articles

Siamese Trackers Based on Deep Features for Visual Tracking

Visual object tracking poses challenges due to deformation of target object appearance, fast motion, brightness change, blocking due to obstacles, etc. In this paper, a Siamese network that is configured using a convolutional neural network is proposed to improve tracking accuracy and robustness. Object tracking accuracy is dependent on features that can well represent objects. Thus, we designed a convolutional neural network structure that can preserve feature information that is produced in the previous layer to extract spatial and semantic information. Features are extracted from the target object and search area using a Siamese network, and the extracted feature map is input into the region proposal network, where fast Fourier-transform convolution is applied. The feature map produces a probability score for the presence of an object region and an object in a region, where the similarities are high to search the target. The network was trained with a video dataset called ImageNet Large Scale Visual Recognition Challenge. In the experiment, quantitative and qualitative evaluations were conducted using the object-tracking benchmark dataset. The evaluation results indicated competitive results for some video attributes through various experiments. By conducting experiments, the proposed method achieved competitive results for some video attributes, with a success metric of 0.632 and a precision metric of 0.856 as quantitative values.

Adaptive source localization for mobile robots based on Kriging prediction

This paper addresses the source localization for mobile robots under the assumption of spatio-temporal invariance. Two kriging-based source localization methods, namely global traversal and adaptive gradient extremum, are proposed and implemented using limited sampling data. The global traversal method controls the robot to traverse the whole region according to a fixed trajectory, and finally fits the information distribution of the sources in the whole target region, so as to obtain the location and number of sources. The adaptive gradient extremum method initially controls the robot to collect data by traversing the target search area. Simultaneously, it uses the collected data to fit the source distribution across the entire region. Then, it utilizes gradient and extremum principles to determine the next target point iteratively, eventually reaching the positions of the sources. The simulation results show that the global traversal can obtain more field distribution information, and the adaptive gradient extremum method is more efficient.

Siamese visual tracking with multilayer feature fusion and corner distance IoU loss

The tracker based on the Siamese network regards tracking tasks as solving a similarity problem between the target template and search area. Using shallow networks and offline training, these trackers perform well in simple scenarios. However, due to the lack of semantic information, they have difficulty meeting the accuracy requirements of the task when faced with complex backgrounds and other challenging scenarios. In response to this problem, we propose a new model, which uses the improved ResNet-22 network to extract deep features with more semantic information. Multilayer feature fusion is used to obtain a high-quality score map to reduce the influence of interference factors in the complex background on the tracker. In addition, we propose a more powerful Corner Distance IoU (intersection over union) loss function so that the algorithm can better regression to the bounding box. In the experiments, the tracker was extensively evaluated on the object tracking benchmark data sets, OTB2013 and OTB2015, and the visual object tracking data sets, VOT2016 and VOT2017, and achieved competitive performance, proving the effectiveness of this method.

DP–MHT–TBD: A Dynamic Programming and Multiple Hypothesis Testing-Based Infrared Dim Point Target Detection Algorithm

The detection and tracking of small targets under low signal-to-clutter ratio (SCR) has been a challenging task for infrared search and track (IRST) systems. Track-before-detect (TBD) is a widely-known algorithm which can solve this problem. However, huge computation costs and storage requirements limit its application. To address these issues, a dynamic programming (DP) and multiple hypothesis testing (MHT)-based infrared dim point target detection algorithm (DP–MHT–TBD) is proposed. It consists of three parts. (1) For each pixel in current frame, the second power optimal merit function-based DP is designed and performed in eight search areas to find the target search area that contains the real target trajectory. (2) In the target search area, the parallel MHT model is designed to save the tree-structured trajectory space, and a two-stage strategy is designed to mitigate the contradiction between the redundant trajectories and the requirements of more trajectories under low SCR. After constant false alarm segmentation of the energy accumulation map, the preliminary candidate points can be obtained. (3) The target tracking method is designed to eliminate false alarms. In this work, an efficient second power optimal merit function-based DP is designed to find the target search area for each pixel, which greatly reduces the trajectory search space. A two-stage MHT model, in which pruning for the tree-structured trajectory space is avoided and all trajectories can be processed in parallel, is designed to further reduce the hypothesis space exponentially. This model greatly reduces computational complexity and saves storage space, improving the engineering application of the TBD method. The DP–MHT–TBD not only takes advantage of the small computation amount of DP and high accuracy of an exhaustive search but also utilizes a novel structure. It can detect a single infrared point target when the SCR is 1.5 with detection probability above 90% and a false alarm rate below 0.01%.

Antiocclusion Visual Tracking Algorithm Combining Fully Convolutional Siamese Network and Correlation Filtering.

Machine learning only uses single-channel grayscale features to model the target, and the filter solution process is relatively simple. When the target has a large change relative to the initial frame, the tracking effect is poor. When there is the same kind of target interference in the target search area, the tracking results will be poor. The tracking algorithm based on the fully convolutional Siamese network can solve these problems. By learning the similarity measurement function, the similarity between the template and the target search area is evaluated, and the target area is found according to the similarity. It adopts offline pre-training and does not update online for tracking, which has a faster tracking speed. According to this study, (1) considering the accuracy and speed, the target tracking algorithm based on correlation filtering performs well. A sample adaptive update model is introduced to eliminate unreliable samples, which effectively enhances the reliability of training samples. With simultaneous changes in illumination and scale, fast motion and in-plane rotation IPR can still be maintained. (2) Determined by calculating the Hessian matrix, in the Struck function, Bike3 parameter adjustment can achieve fast tracking, and Boat5 ensures that the system stability is maintained in the presence of interference factors. The position of the highest scoring point in the fine similarity score map of the same size as the search image is obtained by bicubic interpolation as the target position. (3) The parallax discontinuity caused by the object boundary cannot be directly processed as a smooth continuous parallax. The MeanShift vector obtained by calculating the target template feature and the feature to be searched can increase the accuracy by 53.1%, reduce the robustness by 31.8%, and reduce the error by 28.6% in the SiamVGG algorithm.

Aberrance suppressed spatio-temporal correlation filters for visual object tracking

The objective of the present study is to design a correlation filter-based tracking method for robust visual object tracking. In the literature, numerous tracking methods have been proposed based on discriminative correlation filter (DCF) and obtained impressive performance. However, existing algorithms still face difficulties such as partial occlusion, clutter background, uncertainties, boundary effects (especially when the target search area is small) and other challenging visual factors. Furthermore, during the target detection process, the sudden changes in objects caused by illumination variations and partial/full occlusion degrade the performance. To tackle the drawbacks mentioned earlier, we propose a tracking algorithm concerning the aberrance suppressed correlation filters with spatio-temporal information for visual tracking. Specifically, we introduce a spatial regularization term into the correlation filter to suppresses the boundary effects. Following that, a temporal regularization is adopted into the DCF-based framework to achieve a more robust appearance model and further enhance the tracking performance. In addition, we introduce an approach to suppress the aberrance in response maps caused by the sudden changes. Technically, our proposed method can be directly solved by using the alternating direction method of multipliers (ADMM) technique with a low computational cost. Finally, extensive experimental results on OTB2013, OTB2015, TempleColor128 and UAV123 datasets demonstrate that the proposed method performs favorably against state-of-the-art methods.

Target Adaptive Tracking Based on GOTURN Algorithm with Convolutional Neural Network and Data Fusion.

With the advent of the artificial intelligence era, target adaptive tracking technology has been rapidly developed in the fields of human-computer interaction, intelligent monitoring, and autonomous driving. Aiming at the problem of low tracking accuracy and poor robustness of the current Generic Object Tracking Using Regression Network (GOTURN) tracking algorithm, this paper takes the most popular convolutional neural network in the current target-tracking field as the basic network structure and proposes an improved GOTURN target-tracking algorithm based on residual attention mechanism and fusion of spatiotemporal context information for data fusion. The algorithm transmits the target template, prediction area, and search area to the network at the same time to extract the general feature map and predicts the location of the tracking target in the current frame through the fully connected layer. At the same time, the residual attention mechanism network is added to the target template network structure to enhance the feature expression ability of the network and improve the overall performance of the algorithm. A large number of experiments conducted on the current mainstream target-tracking test data set show that the tracking algorithm we proposed has significantly improved the overall performance of the original tracking algorithm.

Foreground-aware Siamese tracker with dynamic template in wireless sensor networks

Accuracy and reliability are the main problems to be considered when using wireless sensor networks for target tracking. Deep learning has a good prospect in visual object tracking, in which Siamese based trackers achieve a balance between performance and computational efficiency.Template adaptability and feature expression of the target are crucial for Siamese trackers which aim to locate the target by learning a decision-making based similarity evaluation. However, the fixed template can hardly handle the severe target variation and the background information in the complex scene will also interfere the similarity evaluation learning process.In these work, we propose a foreground-aware Siamese tracker with dynamic template to tackle these issues. Firstly, we construct a local effective template feature attention network to guide the template updating according to context tracking information. Then the similarity attention update mask is generated to enhance the discriminative ability of tracker to adapt to complex tracking task. Further, we propose a foreground-aware channel selection module which let the tracker pay more attention to the foreground semantic feature channel in the target search area, thus our tracker can suppress the tracking drift of Siamese trackers in the background clutter scene. Extensive experiments demonstrate that our tracker can significantly improve the performance of our baseline and performs favorably against many state-of-the-art trackers.

SRDT: A Novel Robust RGB-D Tracker Based on Siamese Region Proposal Network and Depth Information

Visual tracking is still a challenging fundamental task in the field of computer vision, especially in complex scenes such as long-term occlusion, nonrigid deformation and fast movement. In this paper, we presented an RGB-D tracker based on the Siamese Region Proposal Network and Depth Information. First, Siamese Network with shared parameters was constructed to perform feature extraction on the target patch and search area. Second, Region Proposal Network was constructed to estimate the target position in the RGB channels. At the same time, the depth information in the RGB-D video was used to determine the target occlusion state and fine-tune the target position. Finally, the tracker used depth information to achieve occlusion recovery when the target was fully occluded. The experimental result shows that the method has better performance in tracking accuracy and tracking speed on the large-scale Princeton RGB-D Tracking Benchmark (PTB) dataset.

Spatial-aware correlation filters with adaptive weight maps for visual tracking

Recently discriminative correlation filter (DCF) methods demonstrate excellent performance for visual tracking. These methods, however, often suffer from boundary effects, especially when the target search area is small. To mitigate boundary effects, a larger target search area is chosen, which, however, introduces many background pixels so that the tracking filter is contaminated by the introduced background pixels and the tracking performance is degraded. In order to alleviate the effects of the background pixels, this paper proposes a spatial-aware adaptive weight map, which wisely assigns large weights to pixels of the target and small weights to pixels in the background. Such desired weight map is adaptively generated by combining the target likelihood, which quantitatively measures whether a pixel belongs to the target or the background, and prior spatial weights of pixels. By integrating the spatial-aware adaptive weight map into the DCF framework, the obtained DCF tracking method can achieve more precise target location and suffer from less tracking drift than those conventional tracking methods. Moreover, we compute a confidence score from the response map and train the tracking filter only in the high-confidence situation. This high-confidence updating strategy can effectively avoid the tracking filter corruption problem when the target is severely occluded and the target search area is mainly filled with pixels of the background. The proposed tracking method is compared with some state-of-the-art methods through extensive experiments on four benchmark datasets, which confirm the performance superiority of the proposed one.

Collaborative Convolution Operators for Real-Time Coarse-to-Fine Tracking

Discriminative correlation filter (DCF) has attracted enormous popularity among the tracking community. Standard DCF based trackers easily achieve real-time tracking speed but significantly suffer from the boundary effects. Recently, spatially regularized or constrained correlation filters tackle the problem of boundary effects at the sacrifice of the closed-form element-wise solution. In this paper, we cope with boundary effects from a novel perspective and present a coarse-to-fine tracking (CTFT) framework which breaks the task of visual tracking into two stages. In the first stage, CTFT locates the target coarsely with a deep convolution operator in a large search area. In the second stage, CTFT performs a fine-grained search of the target with a shallow convolution operator around the initial location in the first stage. With this two-stage tracking framework, CTFT holds a large target search area and maintains the efficient element-wise solution of standard DCF. Compared with state-of-the-art deep trackers, CTFT makes a good balance between computational efficiency and accuracy. Extensive experimental results on OTB2013 and OTB2015 demonstrate that CTFT maintains real-time performance at an average tracking speed of 35.8 fps and achieves favorable performance against state-of-the-art trackers.

A Practical, Robust and Fast Method for Location Localization in Range-Based Systems.

Location localization technology is used in a number of industrial and civil applications. Real time location localization accuracy is highly dependent on the quality of the distance measurements and efficiency of solving the localization equations. In this paper, we provide a novel approach to solve the nonlinear localization equations efficiently and simultaneously eliminate the bad measurement data in range-based systems. A geometric intersection model was developed to narrow the target search area, where Newton’s Method and the Direct Search Method are used to search for the unknown position. Not only does the geometric intersection model offer a small bounded search domain for Newton’s Method and the Direct Search Method, but also it can self-correct bad measurement data. The Direct Search Method is useful for the coarse localization or small target search domain, while the Newton’s Method can be used for accurate localization. For accurate localization, by utilizing the proposed Modified Newton’s Method (MNM), challenges of avoiding the local extrema, singularities, and initial value choice are addressed. The applicability and robustness of the developed method has been demonstrated by experiments with an indoor system.

Surf points based Moving Target Detection and Long-term Tracking in Aerial Videos

A novel method based on Surf points is proposed to detect and lock-track single ground target in aerial videos. Videos captured by moving cameras contain complex motions, which bring difficulty in moving object detection. Our approach contains three parts: moving target template detection, search area estimation and target tracking. Global motion estimation and compensation are first made by grids-sampling Surf points selecting and matching. And then, the single ground target is detected by joint spatial-temporal information processing. The temporal process is made by calculating difference between compensated reference and current image and the spatial process is implementing morphological operations and adaptive binarization. The second part improves KALMAN filter with surf points scale information to predict target position and search area adaptively. Lastly, the local Surf points of target template are matched in this search region to realize target tracking. The long-term tracking is updated following target scaling, occlusion and large deformation. Experimental results show that the algorithm can correctly detect small moving target in dynamic scenes with complex motions. It is robust to vehicle dithering and target scale changing, rotation, especially partial occlusion or temporal complete occlusion. Comparing with traditional algorithms, our method enables real time operation, processing 520×390 frames at around 15fps.