Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion
In this paper, our goal is to improve the recognition accuracy of battlefield target aggregation behavior while maintaining the low computational cost of spatio-temporal depth neural networks. To this end, we propose a novel 3D-CNN (3D Convolutional Neural Networks) model, which extends the idea of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/6/761 |
| _version_ | 1811278040938840064 |
|---|---|
| author | Haiyang Jiang Yaozong Pan Jian Zhang Haitao Yang |
| author_facet | Haiyang Jiang Yaozong Pan Jian Zhang Haitao Yang |
| author_sort | Haiyang Jiang |
| collection | DOAJ |
| description | In this paper, our goal is to improve the recognition accuracy of battlefield target aggregation behavior while maintaining the low computational cost of spatio-temporal depth neural networks. To this end, we propose a novel 3D-CNN (3D Convolutional Neural Networks) model, which extends the idea of multi-scale feature fusion to the spatio-temporal domain, and enhances the feature extraction ability of the network by combining feature maps of different convolutional layers. In order to reduce the computational complexity of the network, we further improved the multi-fiber network, and finally established an architecture—3D convolution Two-Stream model based on multi-scale feature fusion. Extensive experimental results on the simulation data show that our network significantly boosts the efficiency of existing convolutional neural networks in the aggregation behavior recognition, achieving the most advanced performance on the dataset constructed in this paper. |
| first_indexed | 2024-04-13T00:27:35Z |
| format | Article |
| id | doaj.art-2fe42b0aa9a14c9b9cf70f8ca67676e4 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-13T00:27:35Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-2fe42b0aa9a14c9b9cf70f8ca67676e42022-12-22T03:10:33ZengMDPI AGSymmetry2073-89942019-06-0111676110.3390/sym11060761sym11060761Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature FusionHaiyang Jiang0Yaozong Pan1Jian Zhang2Haitao Yang3Space Engineering University, 81 Road, Huairou District, Beijing 101400, ChinaSpace Engineering University, 81 Road, Huairou District, Beijing 101400, ChinaSpace Engineering University, 81 Road, Huairou District, Beijing 101400, ChinaSpace Engineering University, 81 Road, Huairou District, Beijing 101400, ChinaIn this paper, our goal is to improve the recognition accuracy of battlefield target aggregation behavior while maintaining the low computational cost of spatio-temporal depth neural networks. To this end, we propose a novel 3D-CNN (3D Convolutional Neural Networks) model, which extends the idea of multi-scale feature fusion to the spatio-temporal domain, and enhances the feature extraction ability of the network by combining feature maps of different convolutional layers. In order to reduce the computational complexity of the network, we further improved the multi-fiber network, and finally established an architecture—3D convolution Two-Stream model based on multi-scale feature fusion. Extensive experimental results on the simulation data show that our network significantly boosts the efficiency of existing convolutional neural networks in the aggregation behavior recognition, achieving the most advanced performance on the dataset constructed in this paper.https://www.mdpi.com/2073-8994/11/6/761machine visionaggregation behaviorconvolutional neural networkvideoaction recognition |
| spellingShingle | Haiyang Jiang Yaozong Pan Jian Zhang Haitao Yang Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion Symmetry machine vision aggregation behavior convolutional neural network video action recognition |
| title | Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion |
| title_full | Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion |
| title_fullStr | Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion |
| title_full_unstemmed | Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion |
| title_short | Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion |
| title_sort | battlefield target aggregation behavior recognition model based on multi scale feature fusion |
| topic | machine vision aggregation behavior convolutional neural network video action recognition |
| url | https://www.mdpi.com/2073-8994/11/6/761 |
| work_keys_str_mv | AT haiyangjiang battlefieldtargetaggregationbehaviorrecognitionmodelbasedonmultiscalefeaturefusion AT yaozongpan battlefieldtargetaggregationbehaviorrecognitionmodelbasedonmultiscalefeaturefusion AT jianzhang battlefieldtargetaggregationbehaviorrecognitionmodelbasedonmultiscalefeaturefusion AT haitaoyang battlefieldtargetaggregationbehaviorrecognitionmodelbasedonmultiscalefeaturefusion |