A5100604862- Advanced Image and Video Retrieval Techniques
- Visual Attention and Saliency Detection
- Video Surveillance and Tracking Methods
- Image Enhancement Techniques
- Animal Behavior and Welfare Studies
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Flame retardant materials and properties
- Human Pose and Action Recognition
- Advanced Image Fusion Techniques
- Face recognition and analysis
- Smart Agriculture and AI
- Speech and Audio Processing
- Face and Expression Recognition
- Music and Audio Processing
- Image Retrieval and Classification Techniques
- Industrial Vision Systems and Defect Detection
- Parallel Computing and Optimization Techniques
- Computational Drug Discovery Methods
- Anomaly Detection Techniques and Applications
- Embedded Systems Design Techniques
- Computer Graphics and Visualization Techniques
- Fire Detection and Safety Systems
- Advanced Optical Sensing Technologies
South China Agricultural University
2016-2025
Southern Medical University
2024-2025
Nanfang Hospital
2024-2025
Guangdong Institute of Intelligent Manufacturing
2024
Chinese Academy of Medical Sciences & Peking Union Medical College
2024
Peking University
2013-2024
Guangxi Normal University
2023
Fujian Agriculture and Forestry University
2023
Xi'an International Studies University
2023
South China University of Technology
2015-2022
Citrus fruits hold pivotal positions within the agricultural sector. Accurate yield estimation for citrus is crucial in orchard management, especially when facing challenges of fruit occlusion due to dense foliage or overlapping fruits. This study addresses issues low detection accuracy and significant instances missed detections algorithms, particularly scenarios occlusion. It introduces AG-YOLO, an attention-based network designed fuse contextual information. Leveraging NextViT as its...
Online adaptive radiation therapy (ART) promises the ability to deliver an optimal treatment in response daily patient anatomic variation. A major technical barrier for clinical implementation of online ART is requirement rapid image segmentation. Deformable registration (DIR) has been used as automated segmentation method transfer tumor/organ contours from planning images. However, current computational time DIR insufficient ART. In this work, issue addressed by using computer graphics...
The increasing complexity of FPGA-based accelerators, coupled with time-to-market pressure, makes high-level synthesis (HLS) an attractive solution to improve designer productivity by abstracting the programming effort above register-transfer level (RTL). HLS offers various architectural design options different trade-offs via pragmas (loop unrolling, loop pipelining, array partitioning). However, non-negligible runtime renders manual or automated HLS-based exhaustive exploration practically...
Pig behavior recognition and tracking in group-housed livestock are effective aids for health welfare monitoring commercial settings. However, due to demanding farm conditions, the targets pig videos heavily occluded overlapped, there illumination changes, which cause error switches of identify (ID) process decrease quality. To solve these problems, this study proposed an improved DeepSORT algorithm object tracking, contained three processes. Firstly, two detectors, YOLOX-S YOLO v5s, were...
The live weight of pigs has always been an important reference index for growth monitoring and the health status breeding pigs. An accurate acquisition is key to guide scientific feeding improve economic benefits. Compared with traditional contact measurement method, non-contact weighing method can greatly reduce human–pig errors. In this paper, a deep neural network constructed which automatically accurately predict by measuring multiple body parameters. Because good generalization ability...
Quality assessment of image retargeting results is useful when comparing different methods. However, performing the necessary user studies a long, cumbersome process. In this paper, we propose simple yet efficient objective quality method based on five key factors: i) preservation salient regions; ii) analysis influence artifacts; iii) global structure image; iv) compliance with well-established aesthetics rules; and v) symmetry. Experiments RetargetMe benchmark, as well comprehensive...
Obtaining a texture-smoothing and edge-preserving filtered output is significant to image decomposition. Although the edge texture have salient difference in human vision, automatically distinguishing them difficult task, for they similar intensity or gradient response. The state-of-the-art smoothing (EPS) based decomposition approaches are hard obtain satisfactory result. We propose novel suppression filter, exploiting joint bilateral filter as bridge achieve purpose of both properties...
The citrus picking-point localization is critical for automatic harvesting. Due to the complex growing environment and limitations of devices, efficient method becomes a hot research topic. This study designs novel workflow localization, named as CPPL. CPPL achieved based on two stages, namely detection stage segmentation stage. For stage, we define KD-YOLOP accurately detect fruits quickly localize initial picking region. defined knowledge distillation learning model pruning reduce...
This paper presents a real-time three-dimensional (3D) wideband sound localization system designed with miniature XYZO microphone array. Unlike the conventional arrays for using only omnidirectional microphones, presented array is both bidirectional (pressure gradient) and microphones. Therefore, has significantly reduced size known as world's smallest design 3D source in air. In this paper, we describe configuration perform calibration. For localization, provide studies on output model of...
A wide variety of application domains such as networking, computer vision, and cryptography target FPGA platforms to meet computation demand energy consumption constraints. However, design effort for implementations in hardware description languages (HDLs) remains high - often an order magnitude larger than using level (HLLs). Instead development HDLs, synthesis (HLS) tools generate from algorithm descriptions HLLs C/C++/SystemC. HLS promise reduced without the detailed knowledge...
Instance segmentation is an accurate and reliable method to segment adhesive pigs’ images, critical for providing health welfare information on individual pigs, such as body condition score, live weight, activity behaviors in group-housed pig environments. In this paper, a PigMS R-CNN framework based mask scoring (MS R-CNN) explored areas group-pig separate the identification location of pigs. The consists three processes. First, residual network 101-layers, combined with feature pyramid...
The problem of path-finding has to be solved in transportation, city planning, commercial computer games, navigation and many other fields. How find the shortest path is key point this problem. For games fields, since maps are usually not very big, traditional algorithms such as Dijkstra algorithm AStar work well. But if we want two points a big or even country, memory CPU resources limited these may result bad performance. To solve maps, paper introduces analyzes use Hierarchical A-Star...
Accurate detection and counting of live pigs are integral to scientific breeding production in intelligent agriculture. However, existing pig methods challenged by heavy occlusion varying illumination conditions. To overcome these challenges, we proposed IO-YOLOv5 (Illumination-Occlusion YOLOv5), an improved network that expands on the YOLOv5 framework with three key contributions. Firstly, introduced Simple Attention Receptive Field Block (SARFB) module expand receptive field give greater...