[1] X LI, M CHEN, F NIE et al. A multiview-based parameterfree framework for group detection, 4147-4153(2017).

[2] S F LIN, J Y CHEN, H X CHAO. Estimation of number of people in crowded scenes using perspective transformation. IEEE Transactions on Systems， Man， and Cybernetics - Part A： Systems and Humans, 31, 645-654(2001).

[3] T ZHAO, R NEVATIA, B WU. Segmentation and tracking of multiple humans in crowded environments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 1198-1211(2008).

[4] P VIOLA, M J JONES, D SNOW. Detecting pedestrians using patterns of motion and appearance. International Journal of Computer Vision, 63, 153-161(2005).

[5] P KILAMBI, E RIBNICK, A J JOSHI et al. Estimating pedestrian counts in groups. Computer Vision and Image Understanding, 110, 43-59(2008).

[6] [6] 6左静， 巴玉林. 基于多尺度融合的深度人群计数算法［J］. 激光与光电子学进展， 2020， 57（24）： 241502. doi: 10.3788/lop57.241502ZUOJ， BAY L. Population-depth counting algorithm based on multiscale fusion［J］. Laser & Optoelectronics Progress， 2020， 57（24）： 241502.（in Chinese）. doi: 10.3788/lop57.241502

[7] [7] 7赵建敏， 李雪冬， 李宝山. 基于无人机图像的羊群密集计数算法研究［J］. 激光与光电子学进展， 2021， 58（22）： 2210013.ZHAOJ M， LIX D， LIB S. Algorithm of sheep dense counting based on unmanned aerial vehicle images［J］. Laser & Optoelectronics Progress， 2021， 58（22）： 2210013.（in Chinese）

[8] H IDREES, M TAYYAB, K ATHREY et al. Composition loss for counting， density map estimation and localization in dense crowds, 532-546(2018).

[9] M RODRIGUEZ, I LAPTEV, J SIVIC et al. Density-aware person detection and tracking in crowds, 2423-2430(2011).

[10] [10] 10慕晓冬， 白坤， 尤轩昂， 等. 基于对比学习方法的遥感影像特征提取与分类［J］. 光学 精密工程， 2021， 29（9）： 2222-2234. doi: 10.37188/OPE.20212909.2222MUX D， BAIK， YOUX A， et al. Remote sensing image feature extraction and classification based on contrastive learning method［J］. Opt. Precision Eng.， 2021， 29（9）： 2222-2234.（in Chinese）. doi: 10.37188/OPE.20212909.2222

[11] [11] 11周涛， 霍兵强， 陆惠玲， 等. 融合多尺度图像的密集神经网络肺部肿瘤识别算法［J］. 光学 精密工程， 2021， 29（7）： 1695-1708. doi: 10.37188/OPE.20212907.1695ZHOUT， HUOB Q， LUH L， et al. Lung tumor image recognition algorithm with densenet fusion multi-scale images［J］. Opt. Precision Eng.， 2021， 29（7）： 1695-1708.（in Chinese）. doi: 10.37188/OPE.20212907.1695

[12] S Q REN, K M 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).

[13] [13] 13常亮， 邓小明， 周明全， 等. 图像理解中的卷积神经网络［J］. 自动化学报， 2016， 42（9）： 1300-1312. doi: 10.16383/j.aas.2016.c150800CHANGL， DENGX M， ZHOUM Q， et al. Convolutional neural networks in image understanding［J］. Acta Automatica Sinica， 2016， 42（9）： 1300-1312.（in Chinese）. doi: 10.16383/j.aas.2016.c150800

[14] C WANG, H ZHANG, L YANG et al. Deep people counting in extremely dense crowds, 1299-1302(2015).

[15] C ZHANG, H S LI, X G WANG et al. Cross-scene crowd counting via deep convolutional neural networks, 833-841(2015).

[16] Y Y ZHANG, D S ZHOU, S Q CHEN et al. Single-image crowd counting via multi-column convolutional neural network, 589-597(2016).

[17] D B SAM, S SURYA, R V BABU. Switching convolutional neural network for crowd counting, 4031-4039(2017).

[18] L K ZENG, X M XU, B L CAI et al. Multi-scale convolutional neural networks for crowd counting, 465-469(2017).

[19] Y H LI, X F ZHANG, D M CHEN. CSRNet： dilated convolutional neural networks for understanding the highly congested scenes, 1091-1100(2018).

[20] V A SINDAGI, V M PATEL. CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting, 1-6(2017).

[21] W Z LIU, M SALZMANN. Context-aware crowd counting, 5094-5103(2019).

[22] [22] 22张宇倩， 李国辉， 雷军， 等. FF-CAM： 基于通道注意机制前后端融合的人群计数［J］. 计算机学报， 2021， 44（2）： 304-317. doi: 10.11897/SP.J.1016.2021.00304ZHANGY Q， LIG H， LEIJ， et al. FF-CAM： crowd counting based on frontend-backend fusion through channel-attention mechanism［J］. Chinese Journal of Computers， 2021， 44（2）： 304-317.（in Chinese）. doi: 10.11897/SP.J.1016.2021.00304

[23] [23] 23孟月波， 陈宣润， 刘光辉， 等. 高低密度多维视角多元信息融合人群计数方法［J/OL］. 控制与决策：1-10［2022-01-16］.DOI：10.13195/j.kzyjc. 2021.0520.MENGY B， CHENX R， LIUG H， et al. High and low density multi-dimension perspective multivariate information fusion crowd counting method［J/OL］. Control and Decision： 1-10［2022-01-16］.DOI：10.13195/j.kzyjc.2021.0520.（in Chinese）

[24] Z L ZHANG, X Y ZHANG, C PENG et al. ExFuse： Enhancing Feature Fusion for Semantic Segmentation, 269-284(2018).

[25] L C CHEN, G PAPANDREOU, I KOKKINOS et al. DeepLab： semantic image segmentation with deep convolutional nets， atrous convolution， and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848(2018).

[26] M H OH, P OLSEN, K N RAMAMURTHY. Crowd counting with decomposed uncertainty. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 11799-11806(2020).

[27] I HAROON, T MUHMMAD, A KISHAN et al. Composition Loss for Counting， Density Map Estimation and Localization in Dense Crowds, 532-546(2018).

[28] Q WANG, J Y GAO, W LIN et al. Learning from synthetic data for crowd counting in the wild, 8190-8199(2019).

[29] Q WANG, J Y GAO, W LIN et al. NWPU-crowd： a large-scale benchmark for crowd counting and localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 2141-2149(2021).

[30] Z H MA, X WEI, X P HONG et al. Bayesian loss for crowd count estimation with point supervision, 6141-6150(2019).