[1] [1] 1刘媛媛， 张硕， 于海业， 等. 基于语义分割的复杂场景下的秸秆检测［J］. 光学 精密工程， 2020， 28（1）： 200-211. doi: 10.3788/ope.20202801.0200LIUY Y， ZHANGSH， YUH Y， et al. Straw detection algorithm based on semantic segmentation in complex farm scenarios［J］. Opt. Precision Eng.， 2020， 28（1）： 200-211.（in Chinese）. doi: 10.3788/ope.20202801.0200

[2] [2] 2陈彦彤， 李雨阳， 吕石立， 等. 基于深度语义分割的多源遥感图像海面溢油监测［J］. 光学 精密工程， 2020， 28（5）： 1165-1176.CHENY T， LIY Y， LÜSH L， et al. Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation［J］. Opt. Precision Eng.， 2020， 28（5）： 1165-1176.（in Chinese）

[3] [3] 3王中宇， 倪显扬， 尚振东. 利用卷积神经网络的自动驾驶场景语义分割［J］. 光学 精密工程， 2019， 27（11）： 2429-2438. doi: 10.3788/ope.20192711.2429WANGZH Y， NIX Y， SHANGZH D. Autonomous driving semantic segmentation with convolution neural networks［J］. Opt. Precision Eng.， 2019， 27（11）： 2429-2438.（in Chinese）. doi: 10.3788/ope.20192711.2429

[4] K M HE, G GKIOXARI, P DOLLÁR et al. Mask R-CNN, 2980-2988(2017).

[5] O RONNEBERGER, P FISCHER, T BROX. U-net： convolutional networks for biomedical image segmentation, 234-241(2015).

[6] N OTSU. A threshold selection method from gray-level histograms. IEEE Transactions on Systems， Man， and Cybernetics, 9, 62-66(1979).

[7] [7] 7李彦， 赵其峰， 闫河， 等. Canny算子在PCBA目标边缘提取中的优化应用［J］. 光学 精密工程， 2020， 28（9）： 2096-2102. doi: 10.37188/OPE.20202809.2096LIY， ZHAOQ F， YANH， et al. Optimized application of canny operator in PCBA target edge extraction［J］. Opt. Precision Eng.， 2020， 28（9）： 2096-2102.（in Chinese）. doi: 10.37188/OPE.20202809.2096

[8] Q B HOU, M M CHENG, X W HU et al. Deeply supervised salient object detection with short connections(828).

[9] H AGRAWAL, K R DESAI, Y F WANG et al. Nocaps： novel object captioning at scale, 8947-8956(2019).

[10] A KARPATHY, F F LI. Deep visual-semantic alignments for generating image descriptions, 664-676(2015).

[11] O VINYALS, A TOSHEV, S BENGIO et al. Show and tell： a neural image caption generator, 3156-3164(2015).

[12] J JOHNSON, A KARPATHY, F F LI. DenseCap： fully convolutional localization networks for dense captioning, 4565-4574(2016).

[13] L A HENDRICKS, S VENUGOPALAN, M ROHRBACH et al. Deep compositional captioning： describing novel object categories without paired training data, 1-10(2016).

[14] S VENUGOPALAN, L A HENDRICKS, M ROHRBACH et al. Captioning images with diverse objects, 1170-1178(2017).

[15] P ANDERSON, X D HE, C BUEHLER et al. Bottom-up and top-down attention for image captioning and visual question answering, 6077-6086(2018).

[16] G KULKARNI, V PREMRAJ, V ORDONEZ et al. BabyTalk： understanding and generating simple image descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 2891-2903(2013).

[17] P ANDERSON, B FERNANDO, M JOHNSON et al. Guided open vocabulary image captioning with constrained beam search, 945(2017).

[18] S Q REN, K M HE, R GIRSHICK et al. Faster R-CNN： towards real-time object detection with region proposal networks, 1137-1149(2017).

[19] F PERAZZI, J PONT-TUSET, B MCWILLIAMS et al. A benchmark dataset and evaluation methodology for video object segmentation, 724-732(2016).

[20] K Papineni. BLEU ： a method for automatic evaluation of MT. Research Report, W0109, 2001(22176).

[21] S BANERJEE, A LAVIE. METEOR： an automatic metric for MT evaluation with improved correlation with human judgments(2005).

[22] P ANDERSON, B FERNANDO, M JOHNSON et al. SPICE： semantic propositional image caption evaluation, 382-398(2016).