[1] Rong J Z, Yao W, Gao W et al. Fire video detection method based on multi-features fusion[J]. Journal of Combustion Science and Technology, 19, 227-233(2013).

[2] Li J H, Fan R X, Chen Z B. Forest fire recognition based on color and texture features[J]. Journal of South China University of Technology (Natural Science Edition), 48, 70-83(2020).

[3] Borges P V K, Izquierdo E. A probabilistic approach for vision-based fire detection in videos[J]. IEEE Transactions on Circuits and Systems for Video Technology, 20, 721-731(2010).

[4] Zhao F Y, Luo B, Lin G J et al. Flame detection based on improved YOLOv3[J]. China Sciencepaper, 15, 820-826(2020).

[5] Xiong W H, Ren J F, Wu Z H et al. Research on fire identification based on hybrid convolutional neural network[J]. Computer Technology and Development, 30, 81-86(2020).

[6] Yan Y Y, Zhu X Y, Liu Y A et al. Flame detection based on Faster R-CNN model[J]. Journal of Nanjing Normal University (Natural Science Edition), 41, 1-5(2018).

[7] Luo X Q, Pan S L. Improve the fire detection method of YOLOv3[J]. Computer Engineering and Application, 56, 187-196(2020).

[8] Yu L C, Liu J. Flame image recognition algorithm based on improved Mask R-CNN[J]. Computer Engineering and Application, 56, 194-198(2020).

[9] Sun Y C, Pan S G, Zhao T et al. Traffic light detection based on optimized YOLOv3 algorithm[J]. Acta Optica Sinica, 40, 1215001(2020).

[10] Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C], 6517-6525(2017).

[11] Redmon J, Ali F. Yolov3: an incremental improvement[EB/OL]. https://arxiv.org/abs/1804.02767

[12] He T, Zhang Z, Zhang H et al. Bag of tricks for image classification with convolutional neural networks[C], 558-567(2019).

[13] Dai J F, Qi H Z, Xiong Y W et al. Deformable convolutional networks[C], 764-773(2017).

[14] Zhu X Z, Hu H, Lin S et al. Deformable ConvNets V2: more deformable, better results[C], 9300-9308(2019).

[15] Wen N, Guo R Z, He B. Multi-lane vehicle counting based on DCN-Mobile-YOLO model[J]. Journal of Shenzhen University (Science and Engineering), 38, 628-635(2021).

[16] Li G J, Rong Y. Face mask detection algorithm based on DCN-SERes-YOLOv3[J]. Computer and Modernization, 12-20, 30(2021).

[17] Ghiasi G, Lin T Y, Le Q V. DropBlock: a regularization method for convolutional networks[EB/OL]. https://arxiv.org/abs/1810.12890

[18] Zhu H, Ning Q, Lei Y J et al. Fault classification of rolling bearing based on attention mechanism-Inception-CNN Model[J]. Journal of Vibration and Shock, 39, 84-93(2020).

[19] Wu S K, Li X P, Wang X G. IoU-aware single-stage object detector for accurate localization[J]. Image and Vision Computing, 97, 103911(2020).

[20] Ren S Q, He K M, Girshick R et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149(2017).

[21] Cai Z W, Vasconcelos N. Cascade R-CNN: delving into high quality object detection[C], 6154-6162(2018).

[22] Chen J. Research and implementation of target detection based on YOLOv3 algorithm[D](2020).

[23] Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. https://arxiv.org/abs/2004.10934

[24] Lin T Y, Goyal P, Girshick R et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 318-327(2020).