Neighborhood Rough Filter and Intuitionistic Entropy in Unsupervised Tracking
TL;DR: A novel concept, namely, intuitionsistic entropy is introduced here, which consists of two new measures: neighborhood rough entropy and neighborhood probabilistic entropy to deal with the ambiguities that arise due to occurrence of overlapping/ occlusion in a video sequence.
Abstract: This paper aims at developing a novel methodology for unsupervised video tracking by exploring the merits of neighborhood rough sets. A neighborhood rough filter is designed in this process for initial labeling of continuous moving object(s) even in the presence of several variations in different feature spaces. The locations and color models of the object(s) are estimated using their lower–upper approximations in spatio-color neighborhood granular space. Velocity neighborhood granules and acceleration neighborhood granules are then defined over this estimation to predict the object location in the next frame and to speed up the tracking process. A novel concept, namely, intuitionsistic entropy is introduced here, which consists of two new measures: neighborhood rough entropy and neighborhood probabilistic entropy to deal with the ambiguities that arise due to occurrence of overlapping/ occlusion in a video sequence. The unsupervised method of tracking is equally good even when compared with some of the state-of-the art partially supervised methods while showing superior performance during total occlusion.
Citations
More filters
TL;DR: In this article, the authors provide a comprehensive overview of object detection and tracking using deep learning (DL) networks and compare the performance of different object detectors and trackers, including the recent development in granulated DL models.
Abstract: Object detection and tracking is one of the most important and challenging branches in computer vision, and have been widely applied in various fields, such as health-care monitoring, autonomous driving, anomaly detection, and so on. With the rapid development of deep learning (DL) networks and GPU’s computing power, the performance of object detectors and trackers has been greatly improved. To understand the main development status of object detection and tracking pipeline thoroughly, in this survey, we have critically analyzed the existing DL network-based methods of object detection and tracking and described various benchmark datasets. This includes the recent development in granulated DL models. Primarily, we have provided a comprehensive overview of a variety of both generic object detection and specific object detection models. We have enlisted various comparative results for obtaining the best detector, tracker, and their combination. Moreover, we have listed the traditional and new applications of object detection and tracking showing its developmental trends. Finally, challenging issues, including the relevance of granular computing, in the said domain are elaborated as a future scope of research, together with some concerns. An extensive bibliography is also provided.
104 citations
TL;DR: Zhang et al. as discussed by the authors proposed a tri-level granular structure for knowledge-based learning, where the size valuation and logical operation are hierarchically supplemented at higher levels, and the relative and absolute distances of bottom neighborhood granules are linearly combined to a double-quantitative distance.
Abstract: In terms of neighborhood rough sets, the tri-level granular structure of neighborhood system (carrying the neighborhood granule, swarm, and library) establishes a granular computing mechanism for knowledge-based learning. However, its hierarchical exploration is inadequate, while its measurement can be extended for robust applications. Regarding this tri-level granular structure, the double-quantification technology is novelly introduced to make a thorough investigation, especially on the double-quantitative distance measurement and classification learning. Firstly, the size valuation and logical operation are hierarchically supplemented at higher levels. Secondly, the relative and absolute distances of bottom neighborhood granules are linearly combined to a double-quantitative distance, and all the three types of distances are promoted to both the middle swarm level and the top library level. Finally, the double-quantitative distance powerfully characterizing the difference of neighborhood granules is utilized to generate a double-quantitative classifier KNGD, and relevant data experiments show that this new classifier outperforms or balances two existing classifiers, i.e., the relative classifier KNGR and absolute classifier KNGA. By theory, example, and experiment, this study hierarchically perfects the tri-level granular structure of neighborhood system, and the corresponding double-quantification integration and extension offer the robust knowledge measurement and effective classification learning.
42 citations
TL;DR: In this paper , two new models, namely granulated RCNN (G-RCNN) and multi-class deep SORT (MCD-SORT), were developed for object detection and tracking, respectively from videos.
Abstract: In this article, two new models, namely granulated RCNN (G-RCNN) and multi-class deep SORT (MCD-SORT), for object detection and tracking, respectively from videos are developed. Object detection has two stages: object localization (region of interest RoI) and classification. G-RCNN is an improved version of the well-known Fast RCNN and Faster RCNN for extracting RoIs by incorporating the unique concept of granulation in a deep convolutional neural network. Granulation with spatio-temporal information enables more accurate extraction of RoIs (object regions) in unsupervised mode. Compared to Fast and Faster RCNNs, G-RCNN uses (i) granules (clusters) formed over the pooling feature map, instead of its all feature values, in defining RoIs, (ii) only the positive RoIs during training, instead of the whole RoI-map, (iii) videos directly as input, rather than static images, and (iv) only the objects in RoIs, instead of the entire feature map, for performing object classification. All these lead to the improvement in real-time detection speed and accuracy. MCD-SORT is an advanced form of the popular Deep SORT. In MCD-SORT, the searching for association of objects with trajectories is restricted only within the same categories. This increases the performance in multi-class tracking. These characteristic features have been demonstrated over 37 videos containing single-class, two-class, and multi-class objects. Superiority of the models over several state-of-the-art methodologies is also established extensively, both qualitatively and quantitatively.
32 citations
TL;DR: This study focuses on the predictions pertinent to the sustainability of battery life in IoT frameworks in the marine environment and proposes a DNN model that justifies its superiority on the basis of performance metrics such as Mean Squared Error, Mean Absolute Error, Root Mean Squaring Error, and Test Variance Score.
Abstract: Internet of Things (IoT) and related applications have successfully contributed towards enhancing the value of life in this planet. The advanced wireless sensor networks and its revolutionary computational capabilities have enabled various IoT applications become the next frontier, touching almost all domains of life. With this enormous progress, energy optimization has also become a primary concern with the need to attend to green technologies. The present study focuses on the predictions pertinent to the sustainability of battery life in IoT frameworks in the marine environment. The data used is a publicly available dataset collected from the Chicago district beach water. Firstly, the missing values in the data are replaced with the attribute mean. Later, one-hot encoding technique is applied for achieving data homogeneity followed by the standard scalar technique to normalize the data. Then, rough set theory is used for feature extraction, and the resultant data is fed into a Deep Neural Network (DNN) model for the optimized prediction results. The proposed model is then compared with the state of the art machine learning models and the results justify its superiority on the basis of performance metrics such as Mean Squared Error, Mean Absolute Error, Root Mean Squared Error, and Test Variance Score.
28 citations
Cites methods from "Neighborhood Rough Filter and Intui..."
...[34] Make use of Neighborhood Rough Set (NRS) in exploiting the uncertainty of tracking the object in a video sequence....
[...]
TL;DR: In this article, a conceptual framework is proposed for the development of a video surveillance-based system for improving road safety, based on the framework, a set of algorithms are developed which are capable of detecting various traffic pre-events from traffic videos, such as speed violation, one-way traffic, overtaking, illegal parking, and wrong drop-off location of passengers.
25 citations
References
More filters
TL;DR: The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends to discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.
Abstract: The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends. Object tracking, in general, is a challenging problem. Difficulties in tracking objects can arise due to abrupt object motion, changing appearance patterns of both the object and the scene, nonrigid object structures, object-to-object and object-to-scene occlusions, and camera motion. Tracking is usually performed in the context of higher-level applications that require the location and/or shape of the object in every frame. Typically, assumptions are made to constrain the tracking problem in the context of a particular application. In this survey, we categorize the tracking methods on the basis of the object and motion representations used, provide detailed descriptions of representative methods in each category, and examine their pros and cons. Moreover, we discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.
5,318 citations
"Neighborhood Rough Filter and Intui..." refers background in this paper
...The tracking problem has been studied over decades [1]–[4] and there exist several literatures for supervised, partially supervised (with initial manual interactions, i....
[...]
TL;DR: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.
Abstract: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking.
4,996 citations
"Neighborhood Rough Filter and Intui..." refers methods in this paper
...Kernel-based tracking [35] is another popular method in visual tracking of nonrigid objects....
[...]
TL;DR: A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.
Abstract: The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with translated and scaled sample patches. Such sets of samples are riddled with redundancies—any overlapping pixels are constrained to be the same. Based on this simple observation, we propose an analytic model for datasets of thousands of translated patches. By showing that the resulting data matrix is circulant, we can diagonalize it with the discrete Fourier transform, reducing both storage and computation by several orders of magnitude. Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers. For kernel regression, however, we derive a new kernelized correlation filter (KCF), that unlike other kernel algorithms has the exact same complexity as its linear counterpart. Building on it, we also propose a fast multi-channel extension of linear correlation filters, via a linear kernel, which we call dual correlation filter (DCF). Both KCF and DCF outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite running at hundreds of frames-per-second, and being implemented in a few lines of code (Algorithm 1). To encourage further developments, our tracking framework was made open-source.
4,994 citations
"Neighborhood Rough Filter and Intui..." refers methods in this paper
...Recently a new kernelized correlation filter [13] is derived to handle the problems of multitarget tracking and occlusion....
[...]
TL;DR: An extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria is carried out to identify effective approaches for robust tracking and provide potential future research directions in this field.
Abstract: Object tracking has been one of the most important and active research areas in the field of computer vision. A large number of tracking algorithms have been proposed in recent years with demonstrated success. However, the set of sequences used for evaluation is often not sufficient or is sometimes biased for certain types of algorithms. Many datasets do not have common ground-truth object positions or extents, and this makes comparisons among the reported quantitative results difficult. In addition, the initial conditions or parameters of the evaluated tracking algorithms are not the same, and thus, the quantitative results reported in literature are incomparable or sometimes contradictory. To address these issues, we carry out an extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria to understand how these methods perform within the same framework. In this work, we first construct a large dataset with ground-truth object positions and extents for tracking and introduce the sequence attributes for the performance analysis. Second, we integrate most of the publicly available trackers into one code library with uniform input and output formats to facilitate large-scale performance evaluation. Third, we extensively evaluate the performance of 31 algorithms on 100 sequences with different initialization settings. By analyzing the quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.
2,974 citations
"Neighborhood Rough Filter and Intui..." refers background in this paper
..., indoor/outdoor surveillance [37]–[41], single/multiple moving object(s) [4], [42]–[44], body part(s) movements [45] are considered during the experiment....
[...]
...The tracking problem has been studied over decades [1]–[4] and there exist several literatures for supervised, partially supervised (with initial manual interactions, i....
[...]
01 Jan 1978
TL;DR: An algorithm for tracking multiple targets in a cluttered environment is developed, capable of initiating tracks, accounting for false or missing reports, and processing sets of dependent reports.
Abstract: An algorithm for tracking multiple targets in a cluttered environment is developed. The algorithm is capable of initiating tracks, accounting for false or missing reports, and processing sets of dependent reports. As each measurement is received, probabilities are calculated for the hypotheses that the measurement came from previously known targets in a target file, or from a new target, or that the measurement is false. Target states are estimated from each such data-association hypothesis, using a Kalman filter. As more measurements are received, the probabilities of joint hypotheses are calculated recursively using all available information such as density of unknown targets, density of false targets, probability of detection, and location uncertainty. This branching technique allows correlation of a measurement with its source based on subsequent, as well as previous, data. To keep the number of hypotheses reasonable, unlikely hypotheses are eliminated and hypotheses with similar target estimates are combined. To minimize computational requirements, the entire set of targets and measurements is divided into clusters that are solved independently. In an illustrative example of aircraft tracking, the algorithm successfully tracks targets over a wide range of conditions.
2,703 citations