Walsh–Hadamard-Kernel-Based Features in Particle Filter Framework for Underwater Object Tracking
01 Sep 2020-IEEE Transactions on Industrial Informatics (Institute of Electrical and Electronics Engineers (IEEE))-Vol. 16, Iss: 9, pp 5712-5722
TL;DR: The proposed scheme is quite encouraging in the case of sequences with hazy and degraded, partially occluded, and camouflaged challenges, and the performance evaluation is performed by comparing the scheme with five recent state-of-the-art tracking schemes.
Abstract: One of the well-established research domains among computer vision scientists is object tracking. However, not much work has been done in underwater scenarios. This article addresses the problem of visual tracking in the underwater environment with the stationary and nonstationary camera setups. In order to deal with the underwater optical dynamics, a dominant color component-based scene representation is employed in the YCbCr color space. An adaptive approach is devised to select the Walsh–Hadamard (WH) kernels for the efficient extraction of color, edge, and texture strengths, whereas a new feature called range strength is proposed to extract the variation of intensity from underwater sequences in the local neighborhood using the WH kernel. The likelihood of these feature strengths is integrated in a particle filter framework to track the object of interest in underwater sequences. The reference feature strengths used in assigning weights to the particles are updated based on the S $\phi$ rensen distance. The coefficients of feature strengths are calculated in such a way that if one feature fails, then its coefficient become insignificant, whereas the more suitable features get higher feature coefficients. The effectiveness of the proposed scheme is evaluated using the underwater video datasets: reefVid, fish4knowledge (F4K), underwaterchangedetection (UWCD), and National Oceanic and Atmospheric Administration (NOAA). The performance evaluation is performed by comparing the scheme with five recent state-of-the-art tracking schemes. The quantitative analysis of the proposed scheme is carried out using three evaluation measures: overall intersection over union , centroid location error , and average tracking error . The performance of the proposed scheme is quite encouraging in the case of sequences with hazy and degraded, partially occluded, and camouflaged challenges.
Citations
More filters
TL;DR: In this paper , a YOLOv3 model with four-scale detection layers (FDL) was proposed to detect combined B-scan and C-scan ground penetrating radar (GPR) images.
35 citations
TL;DR: Zhang et al. as discussed by the authors proposed a macro-epipolar plane image (macro-EPI) representation for multiview images, which highlights both spatial topological and angular information of the target and distractors.
Abstract: Visual object tracking is of great importance in the field of computer vision. One of the main challenges is the difficulty of identifying moving targets from nearby similar distractors with a single-view image of the scene. To overcome this challenge, in this article, we acquire multiview images of the scenes by using a light-field camera. The multiview images are able to capture the 4-D structure instead of the 2-D plane of the objects but are more difficult to process. Therefore, we propose a novel representation for multiview images, i.e., the macro-epipolar plane image (macro-EPI), which highlights both spatial topological and angular information of the target and distractors. It is obtained by slicing the original multiview images into pieces and properly restacking these pieces in an ordinal manner. The resulting macro-EPI is mapped into the 2-D space; therefore, we adapt a modified autoencoder network to train a macro-EPI feature extractor. Thereafter, we design a composite framework of two-pattern convolution filters based on a discriminative correlation filter for object tracking, which successfully discriminates the target from the distractors by merging the macro-EPI features and the single-view image features. The experiments also show that our method outperforms the state-of-the-art methods in the presence of similar distractors.
3 citations
TL;DR: Zhang et al. as discussed by the authors proposed a macro-epipolar plane image (macro-EPI) representation for multiview images, which highlights both spatial topological and angular information of the target and distractors.
Abstract: Visual object tracking is of great importance in the field of computer vision. One of the main challenges is the difficulty of identifying moving targets from nearby similar distractors with a single-view image of the scene. To overcome this challenge, in this article, we acquire multiview images of the scenes by using a light-field camera. The multiview images are able to capture the 4-D structure instead of the 2-D plane of the objects but are more difficult to process. Therefore, we propose a novel representation for multiview images, i.e., the macro-epipolar plane image (macro-EPI), which highlights both spatial topological and angular information of the target and distractors. It is obtained by slicing the original multiview images into pieces and properly restacking these pieces in an ordinal manner. The resulting macro-EPI is mapped into the 2-D space; therefore, we adapt a modified autoencoder network to train a macro-EPI feature extractor. Thereafter, we design a composite framework of two-pattern convolution filters based on a discriminative correlation filter for object tracking, which successfully discriminates the target from the distractors by merging the macro-EPI features and the single-view image features. The experiments also show that our method outperforms the state-of-the-art methods in the presence of similar distractors.
3 citations
TL;DR: In this paper , a Siamese Region Proposal Network (SPN) based tracking algorithm using two weights sharing is applied to track the target in motion, and the tracking rate based on SPN algorithm is up to 180 FPS.
Abstract: Object recognition and tracking is a challenge for underwater vehicles. Traditional algorithm requires a clear feature definition, which suffers from uncertainty as the variation of occlusion, illumination, season and viewpoints. A deep learning approach requires a large amount of training data, which suffers from the computation. The proposed method is to avoid the above drawbacks. The Siamese Region Proposal Network tracking algorithm using two weights sharing is applied to track the target in motion. The key point to overcome is the one-shot detection task when the object is unidentified. Various complex and uncertain environment scenarios are applied to evaluate the proposed system via the deep learning model’s predictions metrics (accuracy, precision, recall, P-R curve, F1 score). The tracking rate based on Siamese Region Proposal Network Algorithm is up to 180 FPS.
2 citations
06 Nov 2020
TL;DR: Wang et al. as discussed by the authors proposed a robust object tracking via graph-based transductive learning with subspace representation (GTLSR), which is based on probabilistic hypergraph ranking theory to capture the local affinity information amount all vertices.
Abstract: Although many tracking algorithms have been studied in recent years, target tracking is still a very basic research topic. In this study, we propose a novel robust object tracking via graph-based transductive learning with subspace representation (GTLSR). Firstly, probabilistic hypergraph ranking theory is developed to capture the local affinity information amount all vertices. Then, we transform the object tracking into the transductive learning problem based on Bayesian inference framework. Third, to deal with the occlusions of target, we use subspace representation to constrain the indication vector of template set. Finally, a dynamic updating strategy based on double threshold is proposed to solve the challenges of pose change and occlusion. The extensive experiments reflect that the proposed GTLSR outperforms other baseline methods in accuracy and robustness.
2 citations
References
More filters
04 Jan 1998
TL;DR: In contrast with filters that operate on the three bands of a color image separately, a bilateral filter can enforce the perceptual metric underlying the CIE-Lab color space, and smooth colors and preserve edges in a way that is tuned to human perception.
Abstract: Bilateral filtering smooths images while preserving edges, by means of a nonlinear combination of nearby image values. The method is noniterative, local, and simple. It combines gray levels or colors based on both their geometric closeness and their photometric similarity, and prefers near values to distant values in both domain and range. In contrast with filters that operate on the three bands of a color image separately, a bilateral filter can enforce the perceptual metric underlying the CIE-Lab color space, and smooth colors and preserve edges in a way that is tuned to human perception. Also, in contrast with standard filtering, bilateral filtering produces no phantom colors along edges in color images, and reduces phantom colors where they appear in the original image.
8,738 citations
"Walsh–Hadamard-Kernel-Based Feature..." refers background in this paper
...4) Range Strength: The range measure indicates the photometric similarity between a pixel and its neighborhood [36]....
[...]
23 Jun 2013
TL;DR: Large scale experiments are carried out with various evaluation criteria to identify effective approaches for robust tracking and provide potential future research directions in this field.
Abstract: Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.
3,828 citations
"Walsh–Hadamard-Kernel-Based Feature..." refers methods in this paper
...The results are reported and analyzed using three performance measures: CLE, ATE, and OIoU indices and found to be performing the best....
[...]
...In this article, the evaluation measures used for the quantitative analysis of the proposed tracking technique are overall intersection over union (OIoU) [2], centroid location error (CLE) [14], and average tracking error (ATE) [2]....
[...]
...The ATE values are reported in Tables II–IV....
[...]
07 Dec 2015
TL;DR: This paper adaptively learn correlation filters on each convolutional layer to encode the target appearance and hierarchically infer the maximum response of each layer to locate targets.
Abstract: Visual object tracking is challenging as target objects often undergo significant appearance changes caused by deformation, abrupt motion, background clutter and occlusion. In this paper, we exploit features extracted from deep convolutional neural networks trained on object recognition datasets to improve tracking accuracy and robustness. The outputs of the last convolutional layers encode the semantic information of targets and such representations are robust to significant appearance variations. However, their spatial resolution is too coarse to precisely localize targets. In contrast, earlier convolutional layers provide more precise localization but are less invariant to appearance changes. We interpret the hierarchies of convolutional layers as a nonlinear counterpart of an image pyramid representation and exploit these multiple levels of abstraction for visual tracking. Specifically, we adaptively learn correlation filters on each convolutional layer to encode the target appearance. We hierarchically infer the maximum response of each layer to locate targets. Extensive experimental results on a largescale benchmark dataset show that the proposed algorithm performs favorably against state-of-the-art methods.
1,812 citations
01 Jan 2007
TL;DR: Various distance/similarity measures that are applicable to compare two probability density functions, pdf in short, are reviewed and categorized in both syntactic and semantic relationships to reveal similarities among numerous distance/Similarity measures.
Abstract: Distance or similarity measures are essential to solve many pattern recognition problems such as classification, clustering, and retrieval problems. Various distance/similarity measures that are applicable to compare two probability density functions, pdf in short, are reviewed and categorized in both syntactic and semantic relationships. A correlation coefficient and a hierarchical clustering technique are adopted to reveal similarities among numerous distance/similarity measures.
1,631 citations
"Walsh–Hadamard-Kernel-Based Feature..." refers background or methods in this paper
...frt+ 1 = θFt + (1 − θ)fr1 (21) where θ is the update regulating parameter, which is equal to the Sφrensen distance [30] between the histogram of the rectangular blob at time t = 0 and t....
[...]
...Hence, in the proposed scheme, reference feature strengths are updated regularly on the basis of Sφrensen distance [30] between the histogram of the tracked blob at any time instant t and (t = 0) of subsequent frames....
[...]
...To compute the likelihood, the reference feature strengths are updated based on the Sφrensen distance [30]....
[...]
TL;DR: It is demonstrated that trackers can be evaluated objectively by survival curves, Kaplan Meier statistics, and Grubs testing, and it is found that in the evaluation practice the F-score is as effective as the object tracking accuracy (OTA) score.
Abstract: There is a large variety of trackers, which have been proposed in the literature during the last two decades with some mixed success. Object tracking in realistic scenarios is a difficult problem, therefore, it remains a most active area of research in computer vision. A good tracker should perform well in a large number of videos involving illumination changes, occlusion, clutter, camera motion, low contrast, specularities, and at least six more aspects. However, the performance of proposed trackers have been evaluated typically on less than ten videos, or on the special purpose datasets. In this paper, we aim to evaluate trackers systematically and experimentally on 315 video fragments covering above aspects. We selected a set of nineteen trackers to include a wide variety of algorithms often cited in literature, supplemented with trackers appearing in 2010 and 2011 for which the code was publicly available. We demonstrate that trackers can be evaluated objectively by survival curves, Kaplan Meier statistics, and Grubs testing. We find that in the evaluation practice the F-score is as effective as the object tracking accuracy (OTA) score. The analysis under a large variety of circumstances provides objective insight into the strengths and weaknesses of trackers.
1,604 citations
"Walsh–Hadamard-Kernel-Based Feature..." refers background in this paper
...The position noise and velocity noise variance for the particle filter are manually fixed between [3, 7], and [1, 4], respectively, for different videos depending on the speed of object motion, speed of changing the shape with respect to the field of view....
[...]