3-D Objects Detection and Tracking Using Solid-State LiDAR and RGB Camera

Zheng, Peng; Xiong, Zhi; Zhao, Yanyun; Zhang, Ling

doi:10.1109/jsen.2023.3279500

Cited by 8 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the Mask R-CNN and LMB based target detection and tracking scheme [22] is based on infrared images. The studies in [23]- [25] rely on devices like lidar for target detection. It is worth noting that these lasers or specialized camera sensors may incur additional cost and also tend to yield sub-optimal data quality in the face of weather variations within the port environment, such as fog, night conditions, or intense brightness.…”

Section: ) Jdt Paradigm Trackingmentioning

confidence: 99%

Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG

YU,

ZHENG,

YANG

et al. 2024

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

Rubber Tire Gantry (RTG) plays a pivotal role in facilitating efficient container handling within port operations. Conventional RTG, highly depending on human operations, is inefficient, labor-intensive and also poses safety issues in adverse environments. This paper introduces a multi-target detection and tracking (MTDT) algorithm specifically tailored for automated port RTG operations. The approach seamlessly integrates enhanced YOLOX for object detection and improved DeepSORT for object tracking to enhance MTDT performance in the complex port settings. In particular, Light-YoloX, an upgraded version of YOLOX incorporating separable convolution and attention mechanism, is introduced to improve real-time capability and small target detection. Subsequently, OSNet-DeepSORT, an enhanced version of DeepSORT, is proposed to mitigate ID switching challenges arising from unreliable data communication or occlusion in real port scenarios. The effectiveness of the proposed method is validated in various real-life port operations. Ablation studies and comparative experiments against typical MTDT algorithms demonstrate noteworthy enhancements in key performance metrics, encompassing small target detection, tracking accuracy, ID switching frequency, and realtime performance.

show abstract

Section: ) Jdt Paradigm Trackingmentioning

confidence: 99%

Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG

YU,

ZHENG,

YANG

et al. 2024

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

show abstract

“…These systems have wide applications in various fields, including precision component inspection, automated assembly, robot navigation, autonomous vehicles, and satellite mapping. Optical ranging can be realized using various techniques, including time-of-flight (ToF), active triangulation, structured light, and holographic interferometry [1][2][3][4][5][6][7][8]. Depending on the application, each technique has unique advantages and disadvantages, which are determined by various factors, such as measurement range, precision, acquisition time, safety, and cost.…”

Section: Introductionmentioning

confidence: 99%

Compressive sensing–based optical two-frequency continuous wave time-of-flight ranging system

Thanh Vu,

Tran,

Pham

2024

Phys. Scr.

View full text Add to dashboard Cite

A time-of-flight–based ranging system constructed by an intensity-modulated light source and photodetectors (PDs) is proposed. In the proposed system, the carrier wave, which comprises two cosine waves with different frequencies in the megahertz range, is reconstructed from a few samples obtained by PDs with a kilohertz sampling rate using the compressive sensing technique. This allows the system to observe the distance with very high accuracy and it also extends the measurement range while maintaining the accuracy of an existing system that utilizes a single-frequency carrier.

show abstract

Self-Supervised Learning for Camouflaged Object Detection

Liu,

Ji,

et al. 2024

2024 IEEE 7th International Conference on Electronic Information and Communication Technology (ICEICT)

View full text Add to dashboard Cite

3-D Objects Detection and Tracking Using Solid-State LiDAR and RGB Camera

Cited by 8 publications

References 49 publications

Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG

Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG

Compressive sensing–based optical two-frequency continuous wave time-of-flight ranging system

Self-Supervised Learning for Camouflaged Object Detection

Contact Info

Product

Resources

About