Deep MAnTra: deep learning-based multi-animal tracking for Japanese macaques

Pineda, Riza Rae; Kubo, Takatomi; Shimada, Masaki; Ikeda, Kazushi

doi:10.1007/s10015-022-00837-9

Cited by 7 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applying VR technology in virtual reality space can perceive natural scenes through digitization and simulation, and achieve interaction based on computers. This interactive method can use projection devices to capture image sequence information from different orientations through two cameras, thereby real-time collecting and monitoring parameters such as object movement and environmental temperature [15][16].…”

Section: Intelligent Perceptionmentioning

confidence: 99%

Exploration on Intelligent Interaction Design and User Experience of VR Platform Based on Intelligent Perception and Deep Learning

Zhang,

Zheng,

Yin

et al. 2024

Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development,

View full text Add to dashboard Cite

With the popularization of mobile terminals, the development and application fields of VR (virtual reality) technology are receiving increasing attention. Intelligent interactive systems play an important role in this field, and VR scenarios are a new way of digital information dissemination. This article took user experience as the starting point for research. Firstly, relevant literature at home and abroad was organized and summarized. Secondly, after analyzing the integration of existing mainstream platforms with deep learning (DL) theory, an intelligent interaction design platform based on DL model fusion was designed and developed, and experimental and evaluation results were compared and analyzed based on the algorithm. The test results showed that the overall flexibility of the system's interaction was over 70%; the overall delay rate was within 0.08; the tracking accuracy was above 89%. This indicated that through the optimization of DL algorithms, the intelligent interactive design VR platform can meet user needs.

show abstract

Section: Intelligent Perceptionmentioning

confidence: 99%

Exploration on Intelligent Interaction Design and User Experience of VR Platform Based on Intelligent Perception and Deep Learning

Zhang,

Zheng,

Yin

et al. 2024

Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development,

View full text Add to dashboard Cite

show abstract

“…In wildlife detection, the probability of multiple animals appearing in a single image is high, and there are often cases where animals are similar to the background, making it easy to confuse them with the background. Pineda et al [ 28 ] constructed a Japanese macaque dataset. Due to the good integration of the monkeys and background objects, foreground extraction and detection of objects of interest are the main challenges of this dataset.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Detection Method for Wildlife Based on Deep Learning

Li,

Zhang,

2023

Sensors

View full text Add to dashboard Cite

Wildlife is an important part of natural ecosystems and protecting wildlife plays a crucial role in maintaining ecological balance. The wildlife detection method for images and videos based on deep learning can save a lot of labor costs and is of great significance and value for the monitoring and protection of wildlife. However, the complex and changing outdoor environment often leads to less than satisfactory detection results due to insufficient lighting, mutual occlusion, and blurriness. The TMS-YOLO (Takin, Monkey, and Snow Leopard-You Only Look Once) proposed in this paper is a modification of YOLOv7, specifically optimized for wildlife detection. It uses the designed O-ELAN (Optimized Efficient Layer Aggregation Networks) and O-SPPCSPC (Optimized Spatial Pyramid Pooling Combined with Cross Stage Partial Channel) modules and incorporates the CBAM (Convolutional Block Attention Module) to enhance its suitability for this task. In simple terms, O-ELAN can preserve a portion of the original features through residual structures when extracting image features, resulting in more background and animal features. However, O-ELAN may include more background information in the extracted features. Therefore, we use CBAM after the backbone to suppress background features and enhance animal features. Then, when fusing the features, we use O-SPPCSPC with fewer network layers to avoid overfitting. Comparative experiments were conducted on a self-built dataset and a Turkish wildlife dataset. The results demonstrated that the enhanced TMS-YOLO models outperformed YOLOv7 on both datasets. The mAP (mean Average Precision) of YOLOv7 on the two datasets was 90.5% and 94.6%, respectively. In contrast, the mAP of TMS-YOLO in the two datasets was 93.4% and 95%, respectively. These findings indicate that TMS-YOLO can achieve more accurate wildlife detection compared to YOLOv7.

show abstract

Deep Learning Algorithms in Predictive Models for Image Optimization Methods for Civil Engineering Supervision

Zhu

2024

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Deep MAnTra: deep learning-based multi-animal tracking for Japanese macaques

Cited by 7 publications

References 36 publications

Exploration on Intelligent Interaction Design and User Experience of VR Platform Based on Intelligent Perception and Deep Learning

Exploration on Intelligent Interaction Design and User Experience of VR Platform Based on Intelligent Perception and Deep Learning

Intelligent Detection Method for Wildlife Based on Deep Learning

Deep Learning Algorithms in Predictive Models for Image Optimization Methods for Civil Engineering Supervision

Contact Info

Product

Resources

About