Novel Deep-Learning-Aided Multimodal Target Tracking

Moon, SungTae; Youn, Wonkeun; Bang, Hyochoong

doi:10.1109/jsen.2021.3100588

Cited by 13 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 + l = l 21: End Output: The optimal location is the food source j F FIGURE 3 The pseudo-code of the improved salp swarm algorithm value is found through the similarity function, that is the target.…”

Section: Visual Tracking Based On Improved Salp Salp Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Salp swarm algorithm based on golden section and adaptive and its application in target tracking

Tian¹,

Feng

Zhang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

In order to solve the problem that the conventional tracker is not adapted to the abrupt motion, a tracking algorithm based on the improved salp swarm algorithm (ISSA) was proposed. Visual tracking is considered to be a process of locating the optimal position through the interaction between leaders and followers in successive images. Firstly, the adaptive mechanism of leader and follower is introduced into the original salp swarm algorithm (SSA) to balance the exploitation and exploration of the algorithm. This method can improve the accuracy and effect of tracking. Secondly, the golden‐sine algorithm was used to update the position of followers, considering that the SSA had a single spatial search mode for followers and was easy to fall into the local optimum. By comparing with 19 classical tracking algorithms, qualitative and quantitative analysis is carried out to verify the tracking effect of the proposed method. A large number of experimental results show that the algorithm proposed here has good performance in visual tracking, especially for mutation motion tracking.

show abstract

Section: Visual Tracking Based On Improved Salp Salp Algorithmmentioning

confidence: 99%

“…Deep learning mostly uses the general target feature expression extracted after off-line training with non-tracking data set for online target tracking. Tracking algorithms based on CF [1,2] and deep learning [3,4] have been successfully put forward one after another, which makes a big breakthrough in target tracking.…”

Section: Introductionmentioning

confidence: 99%

Salp swarm algorithm based on golden section and adaptive and its application in target tracking

Tian¹,

Feng

Zhang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Considering the computer vision detection technology based on deep learning, it can be influenced by external factors in practical applications, making the detection results biased. e paper applies computer vision principles and introduces attention mechanisms in conventional deep learning networks [7] to establish the multitarget detection framework shown in Figure 1 for feature extraction, feature pooling, and classification regression of camera acquisition images.…”

Section: Computer Vision Multitarget Detection Algorithmsmentioning

confidence: 99%

“…In the formula, L denotes the left camera, A denotes the right camera, χ 1 denotes the projection matrix of the left camera, and χ 2 denotes the projection matrix of the right camera. Based on the left and right camera perspective projection matrix transformation relationships shown in (7) and ( 8), the spatial coordinates of the target can be deduced from the known image point coordinates and the distance measurement results can be obtained by comparing the coordinate information. It is important to note that camera images in complex environments can contain a lot of noise, which can affect the accuracy of the distance measurement results.…”

Section: Target Distance Measurement Programmementioning

confidence: 99%

Research on Multitarget Detection and Intelligent Tracking Technology Based on Computer Vision

Liu¹,

Jun-ya²,

Zhang

2022

Mobile Information Systems

View full text Add to dashboard Cite

With image analysis as the core for multitarget detection and intelligent tracking, mostly applying the Faster R-CNN or YOLO framework, the MOTA score for multitarget tracking is low in the face of complex working environments. Therefore, further research into computer vision techniques is carried out to design new multitarget detection and intelligent tracking methods. Based on the small-aperture imaging model, the principle of lens distortion was analyzed, and a camera calibration and image calibration scheme was designed to obtain effective environmental images. The attention mechanism is introduced to optimise the structure of deep learning networks, and a computer vision detection algorithm based on this is applied to complete regional multitarget detection. The distance between each target and the body is then measured in combination with binocular vision principles. Finally, the spatiotemporal context algorithm is applied to perform simulation calculations to obtain the multitarget intelligent tracking results. The experimental results show that the mean MOTA score of the proposed technique is 0.87 in the night environment, which is 24.14% and 28.374% better than the neural network-based and machine vision-based tracking methods, respectively; in the daytime environment, the mean MOTA score of the multitarget tracking results of the technique is 0.94, which is 28.72%, and the mean MOTA score of 0.94 for the multitarget tracking results in the daytime environment was 28.72% and 22.34% higher than the other two methods.

show abstract

“…In recent years, quadrotor unmanned aerial vehicles (UAVs) have been frequently used in applications related to the Internet of Things [1] or to supplant human efforts in hazardous environments such as disaster sites [2], [3]. As a result, the problem of accurate and reliable quadrotor localization, as an essential requirement for successful mission performance, has received great attention [4]- [6]. The Global Positioning System (GPS) is one of the most representative technologies for location estimation [7].…”

Section: Introductionmentioning

confidence: 99%

A Novel Movable UWB Localization System Using UAVs

Moon

Youn

2022

IEEE Access

View full text Add to dashboard Cite

Recently, interest in ultrawideband (UWB)-based localization systems has increased in various application fields. However, since UWB anchors are usually fixed, they work only within the limited range that UWB measurement signals can reach. To address this issue, a swarm flight system with movable UWB anchors is developed. One ground station controls multiple unmanned aerial vehicles (UAVs), each of which is equipped with a UWB anchor and real-time kinematic global positioning system (RTK-GPS) capabilities, and collects the precise (centimeter-level) positions of the UWB anchor UAVs through RTK-GPS. In this way, the constraints of existing UWB systems can be alleviated by changing the UWB anchor positions in real time as desired by the user. In addition, this paper proposes a novel localization algorithm using only time-of-flight (TOF) measurements from UWB signals, heading information from an attitude and heading reference system (AHRS), and altitude information from a barometer. The results of UAV flight tests show that the proposed algorithm provides better localization performance than existing algorithms.INDEX TERMS Interacting multiple model, Kalman filter, localization, swarm flight system, ultrawideband (UWB), unmanned aerial vehicle (UAV).

show abstract

Novel Deep-Learning-Aided Multimodal Target Tracking

Cited by 13 publications

References 30 publications

Salp swarm algorithm based on golden section and adaptive and its application in target tracking

Salp swarm algorithm based on golden section and adaptive and its application in target tracking

Research on Multitarget Detection and Intelligent Tracking Technology Based on Computer Vision

A Novel Movable UWB Localization System Using UAVs

Contact Info

Product

Resources

About