A5055240281- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- UAV Applications and Optimization
- Robotics and Sensor-Based Localization
- Wildlife Ecology and Conservation
- Remote Sensing and Land Use
- Advanced Measurement and Detection Methods
- Wildlife-Road Interactions and Conservation
- Fire Detection and Safety Systems
- Robotic Path Planning Algorithms
- High voltage insulation and dielectric phenomena
- Advanced Image and Video Retrieval Techniques
- Food Supply Chain Traceability
- Industrial Vision Systems and Defect Detection
- Image and Object Detection Techniques
- Infrared Target Detection Methodologies
North China Institute of Aerospace Engineering
2022-2025
Procapra przewalskii, which inhabits plateau areas, faces the constant threat of poaching and unpredictable risks that impede its survival. The implementation a comprehensive, real-time monitoring tracking system for przewalskii using artificial intelligence unmanned aerial vehicle (UAV) technology is crucial to safeguard existence. Therefore, UAV multi-object-tracking (MOT) with global motion compensation (GMC) was proposed in this study. YOLOv7 Deep SORT were employed object detection...
The existing precision grazing technology helps to improve the utilization rate of livestock pasture, but it is still at level “collectivization” and cannot provide more accurate management control. (1) Background: In recent years, with rapid development agent-related technologies such as deep learning, visual navigation tracking, lightweight edge computing cell target detection algorithms have been proposed. (2) Methods: this study, improved YOLOv5 detector combined extended dataset...
As the global economy expands, waterway transportation has become increasingly crucial to logistics sector. This growth presents both significant challenges and opportunities for enhancing accuracy of ship detection tracking through application artificial intelligence. article introduces a multi-object system designed unmanned aerial vehicles (UAVs), utilizing YOLOv7 Deep SORT algorithms tracking, respectively. To mitigate impact limited data on model training, transfer learning techniques...
The Procapra przewalskii, plays a vital role in sustaining the ecological balance within its habitat, yet it faces significant threats from environmental degradation and illegal poaching activities. In response to this urgent conservation need, article proposes multi-object tracking (MOT) method for unmanned aerial vehicle (UAV). Initially, approach utilizes modified YOLOv7 network, which incorporates Group-Selective Convolution (GSConv) Neck component, effectively enhancing network’s...
This paper presents an autonomous unmanned-aerial-vehicle (UAV) tracking system based on improved long and short-term memory (LSTM) Kalman filter (KF) model. The can estimate the three-dimensional (3D) attitude precisely track target object without manual intervention. Specifically, YOLOX algorithm is employed to recognize object, which then combined with KF model for precise recognition. In LSTM-KF model, three different LSTM networks (f, Q, R) are adopted a nonlinear transfer function...
As the habitat areas of Tibetan antelopes usually exhibit poaching and unpredictable risks, combining target recognition tracking with intelligent Unmanned Aerial Vehicle (UAV) technology is necessary to obtain real-time location injured better protect rescue them. (1) Background: The most common way track an object detect each frame it, it not run tracker classifier at same rate, because speed for them change class slower than objects move. Especially in edge reasoning scene, UAV monitoring...
It is a challenging and meaningful task to carry out drone-based livestock monitoring in high-altitude cold regions. The purpose of AI execute automated tasks solve practical problems actual applications by combining the software technology with hardware carrier create integrated advanced devices. Only this way, maximum value could be realized. In paper, real-time tracking system dynamic target ability proposed. developed based on tracking-by-detection architecture using YOLOv7 DeepSORT...
This study proposes a method of autonomous navigation UAV for oil and gas pipeline (OGP) dial detection based on the improved YOLOv7 model. The canny edge algorithm is applied in identifying edges pipeline, Hough transform used to detect straight line. intelligent P600 guided patrol dials (OGD) along trained YOLOv7-based model adopted identify OGD data. Dial recognition divided into two stages, that is, contour reading recognition. For rate (RR), Levenstein distance, commonly method,...