Infrared Pedestrian Detection Based on Cross-scale Feature Aggregation and Hierarchical Attention Mapping

Shuai HAO; Shan GAO; Xu MA; Beiyi AN; Tian HE; Hu WEN; Feng WANG

doi:10.3788/gzxb20225106.0610006

[1] Shuigen WEI, Chengwei WANG, Zhen CHEN et al. Infrared dim target detection based on human visual mechanism. Acta Photonica Sinica, 50, 0110001(2021).

[2] Yifan JIAO, Hantao YAO, Changsheng XU. SAN: selective alignment network for cross-domain pedestrian detection. IEEE Transactions on Image Processing, 30, 2155-2167(2021).

[3] Tianshan LIU, K M LAM, Rui ZHAO et al. Deep cross-modal representation learning and distillation for illumination-invariant pedestrian detection. IEEE Transactions on Circuits and Systems for Video Technology, 32, 315-329(2022).

[4] Zizhuang SONG, Jiawei YANG, Dongfang ZHANG et al. Low-altitude sea surface infrared object detection based on unsupervised domain adaptation. Acta Optica Sinica, 42, 0415001(2022).

[5] Shuangchen WU, Zhengrong ZUO. Small target detection in infrared images using deep convolutional neural networks. Journal of Infrared and Millimeter Waves, 38, 371-380(2019).

[6] W CHEUNG, G HAMARNEH. N-SIFT: n-dimensional scale invariant feature transform. IEEE Transactions on Image Processing, 18, 2012-2021(2009).

[7] N DALAI, B TRIGGS. Histograms of oriented gradients for human detection, 886-893(2005).

[8] C J ZHANG, J LIU, C LIANG et al. Image classification using Harr-like transformation of local features with coding residuals. Signal Processing, 93, 2111-2118(2013).

[9] Y SAID, M ATRI, R TOURKI. Human detection based on integral histograms of oriented gradients and SVM, 1-5(2011).

[10] J BEGARD, N ALLEZARD, P SAYD. Real-time human detection in urban scenes: local descriptors and classifiers selection with adaboost-like algorithms, 1-8(2008).

[11] S K BISWAS, P MILANFAR. Linear support tensor machine with LSK Channels: pedestrian detection in thermal infrared images. IEEE Transactions on Image Processing, 26, 4229-4242(2017).

[12] M HIRANMAI, K B NIRANJANA, H K NAGARAJ. Comparative study of various feature extraction techniques for pedestrian detection. Procedia Computer Science, 154, 622-628(2019).

[13] Yande LIU, Tiwei ZENG, Dongbin CHEN et al. Pedestrian detection based on cascade two stage classification. Electronic Measurement Technology, 41, 1-6(2018).

[14] Junming LIU, Weihua MENG. Infrared small target detection based on fully convolutional neural network and visual saliency. Acta Photonica Sinica, 49, 0710003(2020).

[15] Hongbin WANG, Song XIAO, Jiahui QU et al. Pansharpening based on multi-branch CNN. Acta Optica Sinica, 41, 0710001(2021).

[16] C ZHU, Y HE, M SAVVIDES. Feature selective anchor-free module for single-shot object detection, 840-849(2020).

[17] Z TIAN, C SHEN, H CHENG. FCOS: fully convolutional one-stage object detection, 9626-9635(2020).

[18] R GIRSHICK, J DONAHUE, T DARRELL et al. Rich feature hierarchies for accurate object detection and semantic segmentation, 580-587(2014).

[19] R GIRSHICK. Fast R-CNN, 1440-1448(2015).

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

[21] Jianan LI, Xiaodan LIANG, Shengmei SHEN et al. Scale-aware fast R-CNN for pedestrian detection. IEEE Transactions on Multimedia, 20, 985-996(2018).

[22] Liliang ZHANG, liang LIN, X LIANG. Is faster R-CNN doing well for pedestrian detection, 443-457(2016).

[23] W LIU, D ANGUELOV, D ERHAN. SSD: single shot multibox detector, 21-37(2016).

[24] J REDMON, S DIVVALA, R GIRSHICK et al. You only look once: unified, real-time object detection, 779-788(2016).

[25] J REDMON, A FARHADI. YOLO9000: better, faster, stronger, 6517-6525(2017).

[26] J REDMON, A FARHADI. YOLOv3: An incremental improvement. https://arxiv.org/abs/1804.02767

[27] A BOCHKOVSKIY, C Y WANG, H Y LIAO. YOLOv4: optimal speed and a accuracy of object detection. https://arxiv.org/abs/2004.10934

[28] Bin ZHAO, Chunping WANG, Qiang FU et al. Multi-scale infrared pedestrian detection based on deep Attention Mechanism. Acta Optica Sinica, 40, 0504001(2020).

[29] B Y WEN, M Q WU. Study on pedestrian detection based on an improved YOLOv4 algorithm, 1198-1202(2020).

[30] S J DU, P ZHANG, B F ZHANG et al. Weak and occluded vehicle detection in complex infrared environment based on improved YOLOv4. IEEE Access, 9, 25671-25680(2021).

[31] S WOO, J PARK, J LEE. CBAM: convolutional block attention module, 3-19(2018).

[32] J W DAVIS, V SHARMA. Background-subtraction using contour-based fusion of thermal and visible imagery. Computer Vision & Image Understanding, 106, 162-182(2007).

[33] J W DAVIS, M A KECK. A two-stage template approach to person detection in thermal imagery, 364-369(2005).