MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation
Conflicts between humans and animals in agricultural and settlement areas have recently increased, resulting in significant resource loss and risks to human and animal lives. This growing issue presents a global challenge. This paper addresses the detection and identification of offending animals, p...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/15/2/259 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589345840693248 |
|---|---|
| author | Haiyan Zhang Huiqi Li Guodong Sun Feng Yang |
| author_facet | Haiyan Zhang Huiqi Li Guodong Sun Feng Yang |
| author_sort | Haiyan Zhang |
| collection | DOAJ |
| description | Conflicts between humans and animals in agricultural and settlement areas have recently increased, resulting in significant resource loss and risks to human and animal lives. This growing issue presents a global challenge. This paper addresses the detection and identification of offending animals, particularly in obscured or blurry nighttime images. This article introduces Multi-Channel Coordinated Attention and Multi-Dimension Feature Aggregation (MDA-DETR). It integrates multi-scale features for enhanced detection accuracy, employing a Multi-Channel Coordinated Attention (MCCA) mechanism to incorporate location, semantic, and long-range dependency information and a Multi-Dimension Feature Aggregation Module (DFAM) for cross-scale feature aggregation. Additionally, the VariFocal Loss function is utilized to assign pixel weights, enhancing detail focus and maintaining accuracy. In the dataset section, this article uses a dataset from the Northeast China Tiger and Leopard National Park, which includes images of six common offending animal species. In the comprehensive experiments on the dataset, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>m</mi><mi>A</mi><msub><mi>P</mi><mn>50</mn></msub></mrow></semantics></math></inline-formula> index of MDA-DETR was 1.3%, 0.6%, 0.3%, 3%, 1.1%, and 0.5% higher than RT-DETR-r18, yolov8n, yolov9-C, DETR, Deformable-detr, and DCA-yolov8, respectively, indicating that MDA-DETR is superior to other advanced methods. |
| format | Article |
| id | doaj-art-9cfe5310202b47128f90ee4e939d645f |
| institution | Kabale University |
| issn | 2076-2615 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj-art-9cfe5310202b47128f90ee4e939d645f2025-01-24T13:18:19ZengMDPI AGAnimals2076-26152025-01-0115225910.3390/ani15020259MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature AggregationHaiyan Zhang0Huiqi Li1Guodong Sun2Feng Yang3School of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaConflicts between humans and animals in agricultural and settlement areas have recently increased, resulting in significant resource loss and risks to human and animal lives. This growing issue presents a global challenge. This paper addresses the detection and identification of offending animals, particularly in obscured or blurry nighttime images. This article introduces Multi-Channel Coordinated Attention and Multi-Dimension Feature Aggregation (MDA-DETR). It integrates multi-scale features for enhanced detection accuracy, employing a Multi-Channel Coordinated Attention (MCCA) mechanism to incorporate location, semantic, and long-range dependency information and a Multi-Dimension Feature Aggregation Module (DFAM) for cross-scale feature aggregation. Additionally, the VariFocal Loss function is utilized to assign pixel weights, enhancing detail focus and maintaining accuracy. In the dataset section, this article uses a dataset from the Northeast China Tiger and Leopard National Park, which includes images of six common offending animal species. In the comprehensive experiments on the dataset, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>m</mi><mi>A</mi><msub><mi>P</mi><mn>50</mn></msub></mrow></semantics></math></inline-formula> index of MDA-DETR was 1.3%, 0.6%, 0.3%, 3%, 1.1%, and 0.5% higher than RT-DETR-r18, yolov8n, yolov9-C, DETR, Deformable-detr, and DCA-yolov8, respectively, indicating that MDA-DETR is superior to other advanced methods.https://www.mdpi.com/2076-2615/15/2/259object detectionRT-DETRtransformercomputer visionattention mechanism |
| spellingShingle | Haiyan Zhang Huiqi Li Guodong Sun Feng Yang MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation Animals object detection RT-DETR transformer computer vision attention mechanism |
| title | MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation |
| title_full | MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation |
| title_fullStr | MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation |
| title_full_unstemmed | MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation |
| title_short | MDA-DETR: Enhancing Offending Animal Detection with Multi-Channel Attention and Multi-Scale Feature Aggregation |
| title_sort | mda detr enhancing offending animal detection with multi channel attention and multi scale feature aggregation |
| topic | object detection RT-DETR transformer computer vision attention mechanism |
| url | https://www.mdpi.com/2076-2615/15/2/259 |
| work_keys_str_mv | AT haiyanzhang mdadetrenhancingoffendinganimaldetectionwithmultichannelattentionandmultiscalefeatureaggregation AT huiqili mdadetrenhancingoffendinganimaldetectionwithmultichannelattentionandmultiscalefeatureaggregation AT guodongsun mdadetrenhancingoffendinganimaldetectionwithmultichannelattentionandmultiscalefeatureaggregation AT fengyang mdadetrenhancingoffendinganimaldetectionwithmultichannelattentionandmultiscalefeatureaggregation |