scholarly journals Multiple objects tracking in the UAV system based on hierarchical deep high-resolution network

2021 ◽  
Author(s):  
Wei Huang ◽  
Xiaoshu Zhou ◽  
Mingchao Dong ◽  
Huaiyu Xu
Keyword(s):  
High Resolution ◽  
Object Tracking ◽  
High Performance ◽  
State Of The Art ◽  
Class Imbalance ◽  
Unified Framework ◽  
Multiple Objects ◽  
Tracking Process ◽  
Objects Tracking ◽  
Different Types

AbstractRobust and high-performance visual multi-object tracking is a big challenge in computer vision, especially in a drone scenario. In this paper, an online Multi-Object Tracking (MOT) approach in the UAV system is proposed to handle small target detections and class imbalance challenges, which integrates the merits of deep high-resolution representation network and data association method in a unified framework. Specifically, while applying tracking-by-detection architecture to our tracking framework, a Hierarchical Deep High-resolution network (HDHNet) is proposed, which encourages the model to handle different types and scales of targets, and extract more effective and comprehensive features during online learning. After that, the extracted features are fed into different prediction networks for interesting targets recognition. Besides, an adjustable fusion loss function is proposed by combining focal loss and GIoU loss to solve the problems of class imbalance and hard samples. During the tracking process, these detection results are applied to an improved DeepSORT MOT algorithm in each frame, which is available to make full use of the target appearance features to match one by one on a practical basis. The experimental results on the VisDrone2019 MOT benchmark show that the proposed UAV MOT system achieves the highest accuracy and the best robustness compared with state-of-the-art methods.

Re-Identification with Pre-Filtering by Image Quality for Multiple Objects Tracking

2021 ◽  
Vol 27 (8) ◽  
pp. 409-418
Author(s):  
A. D. Grigorev ◽  
◽  
A. N. Gneushev ◽  
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Object Tracking ◽  
Multiple Object Tracking ◽  
Tracking Problem ◽  
Multiple Objects ◽  
Multiple Object ◽  
Objects Tracking ◽  
Error Accumulation ◽  
The Stability

The paper considers multiple object tracking. Existing methods tend to be either resource-intensive or prone to high object densities errors failing to provide competitive performance at high frame rates without significant tracking disruptions and error accumulation. We formulate the multiple object tracking problem under the assumption of linearity and independence of the movement of objects. The factorization of the posterior distribution of objects' parameters provides proof of the equivalence of the initial problem and the tracking procedure containing two subtasks: track prediction and assignment of measurements and objects. A modification of the assignment cost is introduced to achieve the stability of assignments in challenging scenarios of tracking, such as multiple objects occlusions and missing detections. We consider adding a term that states to re-identification of the candidate by comparing its descriptor with descriptors from the track history. Given that track measurements are not equal in terms of usefulness for re-identification, we introduce the technique of track descriptor pre-filtering based on quality assessment in order to select the most relevant descriptors for re-identification and reduce method algorithmic complexity. Both known quality assessment methods and an alternative detector-based approach are taken into account. Computational experiments were conducted on MOT20-01, MOT20-02 datasets containing CCTVcameras data in order to compare the proposed method with other approaches. The results showed the computational efficiency of the proposed methods and the increased stability of tracking in complex scenarios.

scholarly journals Improving undersampling-based ensemble with rotation forest for imbalanced problem

2019 ◽  
pp. 1371-1386 ◽  
Author(s):  
Huaping GUO ◽  
Xiaoyu DIAO ◽  
Hongbing LIU
Keyword(s):  
High Performance ◽  
State Of The Art ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Ensemble Methods ◽  
Sampling Technique ◽  
Robust Methods ◽  
Limited Data ◽  
Minority Class ◽  
Rotation Forest

As one of the most challenging and attractive issues in pattern recognition and machine learning, the imbalanced problem has attracted increasing attention. For two-class data, imbalanced data are characterized by the size of one class (majority class) being much larger than that of the other class (minority class), which makes the constructed models focus more on the majority class and ignore or even misclassify the examples of the minority class. The undersampling-based ensemble, which learns individual classifiers from undersampled balanced data, is an effective method to cope with the class-imbalance data. The problem in this method is that the size of the dataset to train each classifier is notably small; thus, how to generate individual classifiers with high performance from the limited data is a key to the success of the method. In this paper, rotation forest (an ensemble method) is used to improve the performance of the undersampling-based ensemble on the imbalanced problem because rotation forest has higher performance than other ensemble methods such as bagging, boosting, and random forest, particularly for small-sized data. In addition, rotation forest is more sensitive to the sampling technique than some robust methods including SVM and neural networks; thus, it is easier to create individual classifiers with diversity using rotation forest. Two versions of the improved undersampling-based ensemble methods are implemented: 1) undersampling subsets from the majority class and learning each classifier using the rotation forest on the data obtained by combing each subset with the minority class and 2) similarly to the first method, with the exception of removing the majority class examples that are correctly classified with high confidence after learning each classifier for further consideration. The experimental results show that the proposed methods show significantly better performance on measures of recall, g-mean, f-measure, and AUC than other state-of-the-art methods on 30 datasets with various data distributions and different imbalance ratios.

scholarly journals A Survey on Analog-to-Digital Converter Integrated Circuits for Miniaturized High Resolution Ultrasonic Imaging System

Micromachines ◽  
2022 ◽  
Vol 13 (1) ◽  
pp. 114
Author(s):  
Dongdong Chen ◽  
Xinhui Cui ◽  
Qidong Zhang ◽  
Di Li ◽  
Wenyang Cheng ◽  
...  
Keyword(s):  
High Resolution ◽  
Integrated Circuits ◽  
High Performance ◽  
Imaging System ◽  
Ultrasonic Imaging ◽  
Pipelined Adc ◽  
Analog To Digital Converter ◽  
Digital Converter ◽  
Analog To Digital ◽  
Different Types

As traditional ultrasonic imaging systems (UIS) are expensive, bulky, and power-consuming, miniaturized and portable UIS have been developed and widely utilized in the biomedical field. The performance of integrated circuits (ICs) in portable UIS obviously affects the effectiveness and quality of ultrasonic imaging. In the ICs for UIS, the analog-to-digital converter (ADC) is used to complete the conversion of the analog echo signal received by the analog front end into digital for further processing by a digital signal processing (DSP) or microcontroller unit (MCU). The accuracy and speed of the ADC determine the precision and efficiency of UIS. Therefore, it is necessary to systematically review and summarize the characteristics of different types of ADCs for UIS, which can provide valuable guidance to design and fabricate high-performance ADC for miniaturized high resolution UIS. In this paper, the architecture and performance of ADC for UIS, including successive approximation register (SAR) ADC, sigma-delta (Σ-∆) ADC, pipelined ADC, and hybrid ADC, have been systematically introduced. In addition, comparisons and discussions of different types of ADCs are presented. Finally, this paper is summarized, and presents the challenges and prospects of ADC ICs for miniaturized high resolution UIS.

scholarly journals Matching Confidence Constrained Bundle Adjustment for Multi-View High-Resolution Satellite Images

2019 ◽  
Vol 12 (1) ◽  
pp. 20 ◽  
Author(s):  
Xiao Ling ◽  
Xu Huang ◽  
Yongjun Zhang ◽  
Gang Zhou
Keyword(s):  
High Resolution ◽  
Satellite Images ◽  
State Of The Art ◽  
Bundle Adjustment ◽  
Adjustment Process ◽  
Unified Framework ◽  
Adjustment Method ◽  
Ground Control Points ◽  
High Resolution Satellite Images ◽  
Experimental Comparisons

Bundle adjustment of multi-view satellite images is a powerful tool to align the orientations of all the images in a unified framework. However, the traditional bundle adjustment process faces a problem in detecting mismatches and evaluating low/medium/high-accuracy matches, which limits the final bundle adjustment accuracy, especially when the mismatches are several times more than the correct matches. To achieve more accurate bundle adjustment results, this paper formulates the prior knowledge of matching accuracy as matching confidences and proposes a matching confidence based bundle adjustment method. The core algorithm firstly selects several highest-confidence matches to initially correct orientations of all images, then detects and eliminates the mismatches under the initial orientation guesses and finally formulates both the matching confidences and the forward-backward projection errors as weights in an iterative bundle adjustment process for more accurate orientation results. We compared our proposed method with the famous RANSAC strategy as well as a state-of-the-art bundle adjustment method on the high-resolution multi-view satellite images. The experimental comparisons are evaluated by image checking points and ground control points, which shows that our proposed method is able to obtain more robust and more accurate mismatch detection results than the RANSAC strategy, even though the mismatches are four times more than the correct matches and it can also achieve more accurate orientation results than the state-of-the-art bundle adjustment method.

HIGH-TEMPERATURE THERMOPLASTIC ELASTOMERS FROM RUBBER–PLASTIC BLENDS: A STATE-OF-THE-ART REVIEW

2017 ◽  
Vol 90 (1) ◽  
pp. 1-36 ◽  
Author(s):  
Shib Shankar Banerjee ◽  
Anil K. Bhowmick
Keyword(s):  
High Temperature ◽  
Automotive Industry ◽  
High Performance ◽  
State Of The Art ◽  
Thermoplastic Elastomers ◽  
Structure And Properties ◽  
Temperature Performance ◽  
Thermoplastic Vulcanizates ◽  
Different Types

ABSTRACT This article reviews different types of high-temperature thermoplastic elastomers and thermoplastic vulcanizates from rubber-plastic blends. Preparation, structure, and properties of these materials are discussed briefly. Strategies to further improve the high-temperature performance of these materials are presented herein. A synopsis of the applications of these high-performance materials in the automotive industry is reported, pointing out the gaps to motivate potential research in this field.

Multiple Object Tracking using YOLO-based Detector

2021 ◽  
Author(s):  
Shinfeng D. Lin ◽  
Tingyu Chang ◽  
Wensheng Chen
Keyword(s):  
Object Tracking ◽  
State Of The Art ◽  
Multiple Object Tracking ◽  
Motion Prediction ◽  
Multiple Object ◽  
Bounding Box ◽  
Video Frames ◽  
Tracking Process ◽  
Tracking By Detection ◽  
Bounding Boxes

In computer vision, multiple object tracking (MOT) plays a crucial role in solving many important issues. A common approach of MOT is tracking by detection. Tracking by detection includes occlusions, motion prediction, and object re-identification. From the video frames, a set of detections is extracted for leading the tracking process. These detections are usually associated together for assigning the same identifications to bounding boxes holding the same target. In this article, MOT using YOLO-based detector is proposed. The authors’ method includes object detection, bounding box regression, and bounding box association. First, the YOLOv3 is exploited to be an object detector. The bounding box regression and association is then utilized to forecast the object’s position. To justify their method, two open object tracking benchmarks, 2D MOT2015 and MOT16, were used. Experimental results demonstrate that our method is comparable to several state-of-the-art tracking methods, especially in the impressive results of MOT accuracy and correctly identified detections.

scholarly journals Siamese Tracking from Single Point Initialization

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 514 ◽  
Author(s):  
Zheng Xu ◽  
Haibo Luo ◽  
Bin Hui ◽  
Zheng Chang
Keyword(s):  
Object Tracking ◽  
State Of The Art ◽  
Single Point ◽  
Contour Detection ◽  
Tracking Accuracy ◽  
Object Contour ◽  
Start Up ◽  
Tracking Process ◽  
Real Time Tracking ◽  
Target Locating

Recently, we have been concerned with locating and tracking vehicles in aerial videos. Vehicles in aerial videos usually have small sizes due to use of cameras from a remote distance. However, most of the current methods use a fixed bounding box region as the input of tracking. For the purpose of target locating and tracking in our system, detecting the contour of the target is utilized and can help with improving the accuracy of target tracking, because a shape-adaptive template segmented by object contour contains the most useful information and the least background for object tracking. In this paper, we propose a new start-up of tracking by clicking on the target, and implement the whole tracking process by modifying and combining a contour detection network and a fully convolutional Siamese tracking network. The experimental results show that our algorithm has significantly improved tracking accuracy compared to the state-of-the-art regarding vehicle images in both OTB100 and DARPA datasets. We propose utilizing our method in real time tracking and guidance systems.

scholarly journals Lossy Geometry Compression for High Resolution Voxel Scenes

2020 ◽  
Vol 3 (1) ◽  
pp. 1-13
Author(s):  
Remi van der Laan ◽  
Leonardo Scandolo ◽  
Elmar Eisemann
Keyword(s):  
High Resolution ◽  
Real Time ◽  
High Performance ◽  
State Of The Art ◽  
Directed Acyclic Graphs ◽  
Memory Consumption ◽  
Geometry Compression ◽  
Acyclic Graphs ◽  
Error Ratio ◽  
Voxel Grid

Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high-resolution binary voxel grid by identifying matching elements. This representation is suitable for high-performance real-time applications, such as free-viewpoint videos and high-resolution precomputed shadows. In this work, we introduce a lossy scheme to further decrease memory consumption by minimally modifying the underlying voxel grid to increase matches. Our method efficiently identifies groups of similar but rare subtrees in an SVDAG structure and replaces them with a single common subtree representative. We test our compression strategy on several standard voxel datasets, where we obtain memory reductions of 10% up to 50% compared to a standard SVDAG, while introducing an error (ratio of modified voxels to voxel count) of only 1% to 5%. Furthermore, we show that our method is complementary to other state of the art SVDAG optimizations, and has a negligible effect on real-time rendering performance.

scholarly journals SORT-YM: An Algorithm of Multi-Object Tracking with YOLOv4-Tiny and Motion Prediction

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2319
Author(s):  
Han Wu ◽  
Chenjie Du ◽  
Zhongping Ji ◽  
Mingyu Gao ◽  
Zhiwei He
Keyword(s):  
Object Tracking ◽  
Research Field ◽  
Tracking Performance ◽  
Motion Prediction ◽  
Tracking Accuracy ◽  
Multiple Objects ◽  
Occluded Objects ◽  
Tracking Process ◽  
Comparison Algorithms ◽  
Public Datasets

Multi-object tracking (MOT) is a significant and widespread research field in image processing and computer vision. The goal of the MOT task consists in predicting the complete tracklets of multiple objects in a video sequence. There are usually many challenges that degrade the performance of the algorithm in the tracking process, such as occlusion and similar objects. However, the existing MOT algorithms based on the tracking-by-detection paradigm struggle to accurately predict the location of the objects that they fail to track in complex scenes, leading to tracking performance decay, such as an increase in the number of ID switches and tracking drifts. To tackle those difficulties, in this study, we design a motion prediction strategy for predicting the location of occluded objects. Since the occluded objects may be legible in earlier frames, we utilize the speed and location of the objects in the past frames to predict the possible location of the occluded objects. In addition, to improve the tracking speed and further enhance the tracking robustness, we utilize efficient YOLOv4-tiny to produce the detections in the proposed algorithm. By using YOLOv4-tiny, the tracking speed of our proposed method improved significantly. The experimental results on two widely used public datasets show that our proposed approach has obvious advantages in tracking accuracy and speed compared with other comparison algorithms. Compared to the Deep SORT baseline, our proposed method has a significant improvement in tracking performance.

Sign in / Sign up

Export Citation Format

Share Document