[1] [1] LIU J J, ZHANG S T, WANG S, et al.. Multi. spectral deep neural networks for pedestrian detec. tion[C]. British Machine Vision Conference, York, UK, 2016: 73. 1-73. 13.

[2] [2] KONIG D, ADAM M, JARVERS C, et al.. Ful. ly convolutional region proposal networks for multi. spectral person detection[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, Hawaii, 2017: 49-56.

[3] [3] REN S Q, HE K M, GIRSHICK R, et al.. Faster R-CNN: Towards real-time object detection with re. gion proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

[4] [4] CAO Y P, GUAN D Y, HUANG W L, et al.. Pedestrian detection with unsupervised multispectral feature learning using deep neural networks[J]. In. formation Fusion, 2019: 206-217.

[5] [5] HOU Y L, SONG Y, HAO X, et al.. Multispec. tral pedestrian detection based on deep convolutional neural networks[J]. Infrared Physics & Technolo. gy, 2018, 94: 69-77.

[6] [6] LEE Y, BUI T D, SHIN J. Pedestrian detection based on deep fusion network using feature correla. tion[C]. Asia-Pacific Signal and Information Pro. cessing Association Annual Summit and Confer. ence. IEEE, 2018: 694-699.

[7] [7] LI C Y, SONG D, TONG R, et al.. Illumination-aware faster R-CNN for robust multispectral pedes. trian detection[J]. Pattern Recognition, 2019, 85: 161-171.

[8] [8] GUAN D Y, CAO Y P, YANG J, et al.. Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection[J]. In. formation Fusion, 2019, 50: 148-157.

[9] [9] ZHANG L, LIU Z, ZHANG S, et al.. Cross-mo. dality interactive attention network for multispectral pedestrian detection[J]. Information Fusion, 2019, 50: 20-29.

[11] [11] LI Z, ZHOU F. FSSD: Feature fusion single shot multibox detector[J/OL]. ArXiv e-prints, 2018-5-17[2020-5-29]. https: //arxiv. org/abs/ 1712. 00960. http://opticsjournal.net/Articles/abstract?aid=OJ201106000142z6C9Fb

[12] [12] LIU W, ANGUELOV D, ERHAN D, et al.. SSD: Single shot multibox detector[C]. Europe. an Conference on Computer Vision, Amsterdam, The Netherlands: Springer, 2016: 21-37.

[14] [14] KIM J, KOH J, KIM Y, et al.. Robust deep multi-modal learning based on gated information fu. sion network[C]. Asian Conference on Computer Vision, Perth, Australia, 2018: 90-106.

[17] [17] HWANG S, PARK J, KIM N, et al.. Multispec. tral pedestrian detection: Benchmark dataset and baseline[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, 2015: 1037-1045.

[18] [18] VANDERSTEEGEN M, VANBEECK K, GO. EDEME T, et al.. Real-Time multispectral pe. destrian detection with a single-pass deep neural network[C]. International Conference on Image Analysis and Recognition, Portugal, 2018: 419-426.

[19] [19] DOLLAR P, WOJEK C, SCHIELE B, et al.. Pedestrian detection: An evaluation of the state of the art[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 743-761.