Computationally efficient deep tracker: Guided MDNet
02 Mar 2017-pp 1-6
TL;DR: The main objective of the paper is to recommend an essential improvement to the existing Multi-Domain Convolutional Neural Network tracker (MDNet) which is used to track unknown object in a video-stream.
Abstract: The main objective of the paper is to recommend an essential improvement to the existing Multi-Domain Convolutional Neural Network tracker (MDNet) which is used to track unknown object in a video-stream. MDNet is able to handle major basic tracking challenges like fast motion, background clutter, out of view, scale variations etc. through offline training and online tracking. We pre-train the Convolutional Neural Network (CNN) offline using many videos with ground truth to obtain a target representation in the network. In online tracking the MDNet uses large number of random sample of windows around the previous target for estimating the target in the current frame which make its tracking computationally complex while testing or obtaining the track. The major contribution of the paper is to give guided samples to the MDNet rather than random samples so that the computation and time required by the CNN while tracking could be greatly reduced. Evaluation of the proposed algorithm is done using the videos from the ALOV300++ dataset and the VOT dataset and the results are compared with the state of art trackers.
Citations
More filters
TL;DR: In this paper, the YOLOv3 pretraining model is used for ship detection, recognition, and counting in the context of intelligent maritime surveillance, timely ocean rescue, and computer-aided decision-making.
Abstract: Automatic ship detection, recognition, and counting are crucial for intelligent maritime surveillance, timely ocean rescue, and computer-aided decision-making. YOLOv3 pretraining model is used for ...
7 citations
03 Jul 2019
TL;DR: A novel face recognition method for population search and criminal pursuit in smart cities and a cloud server architecture for face recognition in smart city environments are proposed.
Abstract: Face recognition technology can be applied to many aspects in smart city, and the combination of face recognition and deep learning can bring new applications to the public security. The use of deep learning machine vision technology and video-based image retrieval technology can quickly and easily solve the current problem of quickly finding the missing children and arresting criminal suspects. The main purpose of this paper is to propose a novel face recognition method for population search and criminal pursuit in smart cities. In large and medium-sized security, the face pictures of the most similar face images can be accurately searched in tens of millions of photos. The storage requires a powerful information processing center for a variety of information storage and processing. To fundamentally support the safe operation of a large system, cloud-based network architecture is considered and a smart city cloud computing data center is built. In addition, this paper proposed a cloud server architecture for face recognition in smart city environments.
1 citations
01 Jan 2018
TL;DR: Visual tracking is a computer vision problem where the task is to follow a target through a video sequence to solve the problem of tracking blindfolded people in the dark.
Abstract: Visual tracking is a computer vision problem where the task is to follow a targetthrough a video sequence. Tracking has many important real-world applications in several fields such as autonomous v ...
Cites methods from "Computationally efficient deep trac..."
...Approaches such as MDnet [37] and SiamFC [2] train their networks to output the location of the target....
[...]
References
More filters
TL;DR: The proposed SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples, and an optimization strategy is proposed, based on the iterative Gauss-Seidel method, for efficient online learning.
Abstract: Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model.
We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.
1,616 citations
"Computationally efficient deep trac..." refers methods in this paper
...The proposed method has been compared with the state of art trackers like MDNet, DeepSRDCF (Deep Spatially Regularized Discriminative Correlation Filters) [22], MUSTer (MUlti-Store Tracker) [20], MEEM (Multiple Expert Entropy minimization) [13], SAMF (Scale Adaptive with Multiple Features) [23], DSST (Discriminative Scale Space Tracker) [24] and KCF [19]....
[...]
...(MUlti-Store Tracker) [20], MEEM (Multiple Expert Entropy minimization) [13], SAMF (Scale Adaptive with Multiple Features) [23], DSST (Discriminative Scale Space Tracker) [24] and KCF [19]....
[...]
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
"Computationally efficient deep trac..." refers methods in this paper
...1) Evaluation Metric: The trackers accuracy and the survival curve is best shown using the evaluation metric F-Score [15]....
[...]
...Evaluation of the proposed scheme has been carried out using some of the videos from ALOV300++ [15] and VOT2016 [27] database....
[...]
...We have carried out the evaluation of the proposed algorithm on about 60 videos from the ALOV300++ dataset [15] and on 15 videos from the VOT2016 dataset [27]....
[...]
17 Jun 2006
TL;DR: A novel algorithm for tracking an object in a video sequence represented by multiple image fragments or patches, which is able to handle partial occlusions or pose change and overcomes several difficulties which cannot be handled by traditional histogram-based algorithms.
Abstract: We present a novel algorithm (which we call "Frag- Track") for tracking an object in a video sequence. The template object is represented by multiple image fragments or patches. The patches are arbitrary and are not based on an object model (in contrast with traditional use of modelbased parts e.g. limbs and torso in human tracking). Every patch votes on the possible positions and scales of the object in the current frame, by comparing its histogram with the corresponding image patch histogram. We then minimize a robust statistic in order to combine the vote maps of the multiple patches. A key tool enabling the application of our algorithm to tracking is the integral histogram data structure [18]. Its use allows to extract histograms of multiple rectangular regions in the image in a very efficient manner. Our algorithm overcomes several difficulties which cannot be handled by traditional histogram-based algorithms [8, 6]. First, by robustly combining multiple patch votes, we are able to handle partial occlusions or pose change. Second, the geometric relations between the template patches allow us to take into account the spatial distribution of the pixel intensities - information which is lost in traditional histogram-based algorithms. Third, as noted by [18], tracking large targets has the same computational cost as tracking small targets. We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (noncolor) information).
1,522 citations
"Computationally efficient deep trac..." refers methods in this paper
...In generative methods, the generative model is described using the target object alone and is used to search the target in the image region with minimum error [1], [2], [3], [19]....
[...]
06 Sep 2014
TL;DR: This paper presents a very appealing tracker based on the correlation filter framework and suggests an effective scale adaptive scheme to tackle the problem of the fixed template size in kernel correlation filter tracker.
Abstract: Although the correlation filter-based trackers achieve the competitive results both on accuracy and robustness, there is still a need to improve the overall tracking capability. In this paper, we presented a very appealing tracker based on the correlation filter framework. To tackle the problem of the fixed template size in kernel correlation filter tracker, we suggest an effective scale adaptive scheme. Moreover, the powerful features including HoG and color-naming are integrated together to further boost the overall tracking performance. The extensive empirical evaluations on the benchmark videos and VOT 2014 dataset demonstrate that the proposed tracker is very promising for the various challenging scenarios. Our method successfully tracked the targets in about 72% videos and outperformed the state-of-the-art trackers on the benchmark dataset with 51 sequences.
1,298 citations
"Computationally efficient deep trac..." refers methods in this paper
...The proposed method has been compared with the state of art trackers like MDNet, DeepSRDCF (Deep Spatially Regularized Discriminative Correlation Filters) [22], MUSTer (MUlti-Store Tracker) [20], MEEM (Multiple Expert Entropy minimization) [13], SAMF (Scale Adaptive with Multiple Features) [23], DSST (Discriminative Scale Space Tracker) [24] and KCF [19]....
[...]
...(MUlti-Store Tracker) [20], MEEM (Multiple Expert Entropy minimization) [13], SAMF (Scale Adaptive with Multiple Features) [23], DSST (Discriminative Scale Space Tracker) [24] and KCF [19]....
[...]
20 Oct 2008
TL;DR: The main idea is to formulate the update process in a semi-supervised fashion as combined decision of a given prior and an on-line classifier, without any parameter tuning, which significantly alleviates the drifting problem in tracking applications.
Abstract: Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the object from its surrounding background needs to be discriminiated. However, on-line adaption faces one key problem: Each update of the tracker may introduce an error which, finally, can lead to tracking failure (drifting). The contribution of this paper is a novel on-line semi-supervised boosting method which significantly alleviates the drifting problem in tracking applications. This allows to limit the drifting problem while still staying adaptive to appearance changes. The main idea is to formulate the update process in a semi-supervised fashion as combined decision of a given prior and an on-line classifier. This comes without any parameter tuning. In the experiments, we demonstrate real-time tracking of our SemiBoost tracker on several challenging test sequences where our tracker outperforms other on-line tracking methods.
1,265 citations
"Computationally efficient deep trac..." refers methods in this paper
...In the case of discriminative methods the model is build using the target and the background simultaneously [5], [4], [7], [11]....
[...]