TY  - JOUR
AU  - Yang, Jiaxun
AU  - Gapar, Yilihamujiang
PY  - 2024
DA  - 2024/05/21
TI  - Improved Object Detection Algorithm Based on Multi-scale and Variability Convolutional Neural Networks
JO  - ICCK Transactions on Emerging Topics in Artificial Intelligence
T2  - ICCK Transactions on Emerging Topics in Artificial Intelligence
JF  - ICCK Transactions on Emerging Topics in Artificial Intelligence
VL  - 1
IS  - 1
SP  - 31
EP  - 43
DO  - 10.62762/TETAI.2024.115892
UR  - https://www.icck.org/article/abs/TETAI.2024.115892
KW  - object detection
KW  - feature pyramid network
KW  - multi-scale fusion
KW  - dynamic convolution
KW  - KITTI
KW  - Caltech
AB  - This paper proposes an improved object detection algorithm based on a dynamically deformable convolutional network (D-DCN), aiming to solve the multi-scale and variability challenges in object detection tasks. First, we review traditional methods in the field of object detection and introduce the current research status of improved methods based on multi-scale and variability convolutional neural networks. Then, we introduce in detail our proposed improved algorithms, including an improved feature pyramid network and a dynamically deformable network. In the improved feature pyramid network, we introduce a multi-scale feature fusion mechanism to better capture target information at different scales. In dynamically deformable networks, we propose dynamic offset calculations and dynamic convolution operations to achieve dynamic adaptation to the target shape and pose. We also validate our method by conducting experiments on the datasets KITTI, NEXET, and Caltech. Finally, we design a comprehensive loss function that considers both location localization error and category classification error to guide model training. Experimental results show that our improved algorithm achieves significant performance improvements in target detection tasks, with higher accuracy and robustness compared with traditional methods. Our work provides an effective method to solve the multi-scale and variability challenges in target detection tasks and has high practical value and prospects for general application.
SN  - 3068-6652
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Yang2024Improved,
  author = {Jiaxun Yang and Yilihamujiang Gapar},
  title = {Improved Object Detection Algorithm Based on Multi-scale and Variability Convolutional Neural Networks},
  journal = {ICCK Transactions on Emerging Topics in Artificial Intelligence},
  year = {2024},
  volume = {1},
  number = {1},
  pages = {31-43},
  doi = {10.62762/TETAI.2024.115892},
  url = {https://www.icck.org/article/abs/TETAI.2024.115892},
  abstract = {This paper proposes an improved object detection algorithm based on a dynamically deformable convolutional network (D-DCN), aiming to solve the multi-scale and variability challenges in object detection tasks. First, we review traditional methods in the field of object detection and introduce the current research status of improved methods based on multi-scale and variability convolutional neural networks. Then, we introduce in detail our proposed improved algorithms, including an improved feature pyramid network and a dynamically deformable network. In the improved feature pyramid network, we introduce a multi-scale feature fusion mechanism to better capture target information at different scales. In dynamically deformable networks, we propose dynamic offset calculations and dynamic convolution operations to achieve dynamic adaptation to the target shape and pose. We also validate our method by conducting experiments on the datasets KITTI, NEXET, and Caltech. Finally, we design a comprehensive loss function that considers both location localization error and category classification error to guide model training. Experimental results show that our improved algorithm achieves significant performance improvements in target detection tasks, with higher accuracy and robustness compared with traditional methods. Our work provides an effective method to solve the multi-scale and variability challenges in target detection tasks and has high practical value and prospects for general application.},
  keywords = {object detection, feature pyramid network, multi-scale fusion, dynamic convolution, KITTI, Caltech},
  issn = {3068-6652},
  publisher = {Institute of Central Computation and Knowledge}
}