A5101797158- Gaze Tracking and Assistive Technology
- Advanced Computing and Algorithms
- Video Surveillance and Tracking Methods
- Visual Attention and Saliency Detection
- Food Industry and Aquatic Biology
- Food Supply Chain Traceability
- Phytochemicals and Antioxidant Activities
- Traditional Chinese Medicine Analysis
- Effects of Environmental Stressors on Livestock
- Agriculture, Soil, Plant Science
- Advanced Measurement and Detection Methods
- Advanced Image Fusion Techniques
- Phytochemistry and Biological Activities
- Brain Tumor Detection and Classification
- Smart Agriculture and AI
- Face and Expression Recognition
- Medical Image Segmentation Techniques
- Insect and Arachnid Ecology and Behavior
- Marine Bivalve and Aquaculture Studies
- Face recognition and analysis
- Animal Nutrition and Physiology
- Animal Behavior and Welfare Studies
- Advanced Neural Network Applications
Inner Mongolia University of Science and Technology
2022-2024
Mongolian University of Science and Technology
2024
Beijing University of Chinese Medicine
2023
Xi'an University of Architecture and Technology
2022
Shaanxi Institute of Zoology
2006
Gaze object prediction is a newly proposed task that aims to discover the objects being stared at by humans. It of great application significance but still lacks unified solution framework. An intuitive incorporate an detection branch into existing gaze method. However, previous methods usually use two different networks extract features from scene image and head image, which would lead heavy network architecture prevent each joint optimization. In this paper, we build novel framework named...
In farming scenarios, cattle identification has become a key issue for the development of precision farming. livestock farming, single-feature recognition methods are prone to misjudgment in complex scenarios involving multiple obscuring each other during drinking and feeding. This paper proposes decision-level method based on multi-feature fusion faces, muzzle patterns, ear tags. The utilizes SOLO algorithm segment images employs FaceNet PP-OCRv4 networks extract features cattle's These...
The dried roots of the perennial herb Angelica sinensis (Oliv.) Diels (AS) are commonly used as medicinal and edible resources. In commercial planting, early bolting flowering (EB) ca. 60% in medicine formation period reduces root yield quality, becoming a significant bottleneck agricultural production. cultivation process, summer (SB) occurs from June to July, autumn (AB) September. AB is often mistaken for AS due its similar morphological characteristics. Few studies have involved whether...
Rumination in cattle is closely related to their health, which makes the automatic monitoring of rumination an important part smart pasture operations. However, manual laborious and wearable sensors are often harmful animals. Thus, we propose a computer vision-based method automatically identify multi-object rumination, calculate time number chews for each cow. The heads video were initially tracked with tracking algorithm, combined You Only Look Once (YOLO) algorithm kernelized correlation...
Image shadow removal is an essential image preprocessing task. In practical production environments, effective methods can significantly enhance the performance of subsequent image-based tasks. However, current for still encounter issues such as artifacts, color deviations, and blurriness due to factors including capturing environment algorithmic efficiency. This paper proposes method using spatial attention, integrating physical deep learning models. By incorporating multi-scale feature...
Abstract Semantic segmentation of remote sensing urban scene images has diverse practical applications, including land cover mapping, change detection, environmental protection, and economic evaluation. However, classical semantic networks encounter challenges such as inadequate utilization multi-scale information imprecise edge target in high-resolution images. In response, this article introduces an efficient network (EMNet) tailored for common features To address these challenges, EMNet...
<title>Abstract</title> In breeding farm cattle feeding and watering scenarios, the number of is dense, resulting in complex scenes spatial congestion, traditional single-modal identification methods often encounter problems such as susceptibility to occlusion low accuracy. Consequently, this study proposes a decision layer fusion identity recognition method with multiple features face, muzzle pattern, ear tag. The image segmented into tag by SOLO algorithm. Cattle patterns adopt FaceNet...
为研究维生素D3对仿刺参(Apostichopus japonicus)幼参生长、体组成及抗氧化能力的影响，在基础饲料中分别添加0(D1)、250(D2)、500(D3)、1000(D4)、2000(D5)、3000(D6) IU/kg的维生素D3(实测值：95、334、570、1076、2063、3081 IU/kg)，制作6组等氮等能的实验饲料，饲喂初始体重为(15.43±0.14) g仿刺参幼参56 d。结果显示，1)维生素D3对仿刺参存活率(SR)无显著影响(P > 0.05)，显著提高了增重率(WGR)和特定生长率(SGR)，D1组均显著低于其他组(P 0.05)。2)维生素D3对体壁水分、粗蛋白和粗脂肪含量无显著影响(P >0.05)；粗灰分含量随添加量的增加呈先升后降趋势，D5组达到最高值；羟脯氨酸含量呈先下降后上升趋势，D4组达到最低值；维生素D3显著提高了体壁Ca含量(P...
Gaze object prediction is a newly proposed task that aims to discover the objects being stared at by humans. It of great application significance but still lacks unified solution framework. An intuitive incorporate an detection branch into existing gaze method. However, previous methods usually use two different networks extract features from scene image and head image, which would lead heavy network architecture prevent each joint optimization. In this paper, we build novel framework named...