基于深度图像增益的RGB-D显著性物体检测

摘要/Abstract

摘要： 深度信息已被证明在显著性物体检测中是一个实用信息，但是深度信息和RGB信息如何更好地实现互补从而达到更高的性能仍是一个值得探究的事情。为此，本文提出一种基于深度图像增益的RGB-D显著性物体检测方法。在双分支的网络结构中增加一个增益子网，采用显著图作差的方法获得深度图片为显著性检测带来的增益，作为增益子网预训练的伪GT。三分支网络分别获取RGB特征、深度特征和深度增益信息，最终将三分支的特征进行融合得到最终的显著性物体检测的结果，增益信息为双分支特征融合提供融合依据。基于深度图像增益的显著性物体检测实验结果表明，该方法得到的显著性物体前景物体更加突出，在多个实验数据集上也有着更优秀的表现。

关键词: 深度信息；显著性物体检测, 图像增益

Abstract: Depth information has been proved to be practical information for salient object detection, but it is still a matter worth exploring that how can the depth information and RGB information complement each other better so as to achieve higher performance. To this end, this paper proposes a RGB-D salient object detection method based on depth image gain. A gain subnet is added to the double-branch network structure, and the gain of the depth image for saliency detection is obtained by the method of saliency map difference, which is used as a pseudo GT for the gain subnet pre-training. The three-branch network separately obtains RGB features, depth features, and depth gain information, and finally fuses the features of the three branches to obtain the final salient object detection result, the gain information provides the fusion basis for the two branch feature fusion. The experimental results of salient object detection based on depth image gain show that the salient object foreground object obtained by this method is more prominent, and it has better performance on multiple experimental datasets.

Key words: depth information, salient object detection, image gain

魏计鹏, 秦国峰. 基于深度图像增益的RGB-D显著性物体检测[J]. 计算机与现代化, 2021, 0(05): 26-30.

WEI Ji-peng, QIN Guo-feng. RGB-D Salient Object Detection Based on Depth Image Gain[J]. Computer and Modernization, 2021, 0(05): 26-30.

参考文献

［1］苏蒙,李为. 一种基于SSD改进的目标检测方法［J］. 计算机与现代化, 2020(2):89-93.
［2］ LIU H Y, JIANG S Q, HUANG Q M, et al. A generic virtual content insertion system based on visual attention analysis［C］// ACM International Conference on Multimedia. 2008:379-388.
［3］ REN Z X, GAO S H, CHIA L T, et al. Region-based saliency detection and its application in object recognition［J］. IEEE Transactions on Circuits And Systems for Video Technology, 2014,24(5):769-779.
［4］吴世海,鲍义东,陈果，等. 基于随机Gabor特征的版参考农作物图像质量评价方法［J］. 计算机与现代化, 2020(4):70-74.〖HJ1.43mm〗
［5］ REN J Q, GONG X, YU L, et al. Exploiting global priors for RGB-D saliency detection［C］// Computer Vision & Pattern Recognition Workshops. 2015:25-32.
［6］ QU L Q, HE S F, ZHANG J W, et al. RGBD salient object detection via deep fusion［J］. IEEE Transactions on Image Processing, 2017,26(5):2274-2285.
［7］ ZHU C B, CAI X, HUANG K, et al. PDNet: Prior-model guided depth-enhanced network for salient object detection［C］// IEEE International Conference on Multimedia and Expo. 2019:199-204.
［8］ WANG N N, GONG X J. Adaptive fusion for RGB-D salient object detection［J］. IEEE Access, 2019,7:55277-55284.
［9］ PIAO Y R, JI W, LI J J, et al. Depth-induced multi-scale recurrent attention network for saliency detection［C］// IEEE/CVF International Conference on Computer Vision. 2020:7254-7263.
［10］ZHAO J X, CAO Y, FAN D P, et al. Contrast prior and fluid pyramid integration for RGBD salient object detection［C］// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020:3922-3931.
［11］RAN J, YANG L, REN T G, et al. Depth-aware salient object detection using anisotropic center-surround difference［J］. Signal Processing: Image Communication, 2015,38(C):115-126.
［12］NIU Y Z, GENG Y J, LI X Q, et al. Leveraging stereopsis for saliency analysis［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2012:454-461.
［13］CHENG Y P, FU H Z, WEI X X, et al. Depth enhanced saliency detection method［C］// ACM International Conference on Internet Multimedia Computing & Service. 2014:23-27.
［14］PENG H W, LI B , XIONG W H, et al. RGBD salient object detection: A benchmark and algorithms［C］// European Conference on Computer Vision. 2014:92-109.
［15］LI N Y, YE J W, JI Y, et al. Saliency detection on light field［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(8):1605-1616.
［16］SIMONYAN K, ZISSERMSN A. Very deep convolutional networks for large-scale image recognition［J］. arXiv preprint arXiv:1409.1556, 2014.
［17］KINGMA D, BA J. Adam: A method for stochastic optimization［J］. arXiv preprint arXiv:1412.6980, 2014.
［18］ABADI M, AGARWAL A, BARHAM P, et al. TensorFlow: Large-scale machine learning on heterogeneous distributed systems［J］. arXiv preprint arXiv:1603.04467, 2016.
［19］FAN D P, CHENG M M, LIU Y, et al. Structure-measure: A new way to evaluate foreground maps［C］// IEEE International Conference on Computer Vision. 2017:4558-4567.

［20］FENG D, BARNES N, YOU S, et al. Local background enclosure for RGB-D salient object detection［C］// Conference on Computer Vision & Pattern Recognition. 2016:2343-2350.

［21］CONG R M, LEI J J, ZHANG C Q, et al. Saliency detection for stereoscopic images based on depth confidence analysis and multiple cues fusion［J］. IEEE Signal Processing Letters, 2016,23(6):819-823.
［22］SONG H K, LIU Z, DU H, et al. Depth-aware salient object detection and segmentation via multiscale discriminative saliency fusion and bootstrap learning［J］. IEEE Transactions on Image Processing, 2017,26(9):4204-4216.
［23］LIANG F F, DUAN L J, MA W, et al. Stereoscopic saliency model using contrast and depth-guided-background prior［J］. Neurocomputing, 2018,275:2227-2238.
［24］HAN J W, CHEN H, LIU N, et al. CNNs-based RGB-D saliency detection via cross-view transfer and multiview fusion［J］. IEEE Transactions on Cybernetics, 2017,48(11):3171-3183.
［25］CHEN H, LI Y . Progressively complementarity-aware fusion network for RGB-D salient object detection［C］// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018:3051-3060.
［26］CHEN H, LI Y F. Three-stream attention-aware network for RGB-D salient object detection［J］. IEEE Transactions on Image Processing, 2019,28(6):2825-2835.
［27］ZHAO J X, CAO Y, FAN D P, et al. Contrast prior and fluid pyramid integration for RGBD salient object detection［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 3927-3936.