基于多尺度特征与注意力模块的室内场景识别方法

doi:10.3969/j.issn.1006-2475.2024.08.007

摘要/Abstract

摘要： 场景识别在视觉信息检索、图像分割、图像/视频理解等任务中有着关键性的作用。随着深度学习理论的发展，尤其是卷积神经网络（CNN）能识别图像中具有辨别性的物体，这大大提高了场景识别的能力。为了实现智能轮椅床等家庭服务机器人的自主场景识别，针对在移动端或嵌入式设备计算资源和内存需求有限的情况下，网络输出辨别性物体单一而造成场景识别率低的问题，提出一种基于多尺度特征提取和注意力模块的室内场景识别方法。该方法基于MobileNetV2轻量化网络，从网络中选择不同分支提取不同尺度的特征。为关注场景中更有辨别性的特征，在分支中加入了MRLA-Light注意力模块，仿真结果表明准确率有明显提高，在MIT Indoor 67数据集、Scene 15数据集上的准确率分别为86.3%和94.3%，相比于同类型网络有更高的准确率。

关键词: 室内场景识别, 轻量化网络, 注意力模块, 特征提取

Abstract: Scene recognition plays an important role in the task of visual information retrieval， segmentation and image/video understanding. With the development of deep learning theory， convolutional neural networks （CNN） greatly improve the ability of scene recognition by recognizing discriminative objects in images. In order to realize autonomous scene recognition for home service robots such as intelligent wheelchair beds， aiming at the condition of limited computing resources and memory requirements of mobile terminals or embedded devices， which leads to low scene recognition rate due to the single discriminative output from the network， an indoor scene recognition method based on multi-scale feature extraction and attention module is proposed. The method is based on MobileNetV2， which selects different branches from the network and extracts features at different scales. To focus on more discriminative features in the scene， the MRLA-Light attention module is added to the branches. The simulation results show that the accuracy is obviously improved， and the accuracy of tests on MIT Indoor 67 and Scene 15 scene datasets reaches 86.3% and 94.3% respectively， which is higher than the same type of networks.

Key words: , indoor scene recognition； lightweight network； attention module； feature extraction

中图分类号:

TP183

岳有军1, 2, 张远锟1, 赵辉1, 2, 王红君1, 2. 基于多尺度特征与注意力模块的室内场景识别方法[J]. 计算机与现代化, 2024, 0(08): 37-42.

YUE Youjun1, 2, ZHANG Yuankun1, ZHAO Hui1, 2, WANG Hongjun1, 2. Indoor Scene Recognition Method Based on Multi-scale Feature and Attention Module[J]. Computer and Modernization, 2024, 0(08): 37-42.

参考文献

［1］ WANG P， WANG J D， ZENG G， et al. Supervised kernel descriptors for visual recognition［C］// 2013 IEEE Conference on Computer Vision and Pattern Recognition. IEEE，2013：2858-2865.
［2］ AFIF M， AYACHI R， SAID Y， et al. Recognizing signs and doors for indoor wayfnding for blind and visually impaired persons［C］// The 5th International Conference on Advanced Technologies for Signal and Image Processing. IEEE， 2020. DOI: 10.1109/ATSIP49331.2020.9231933.
［3］ AFIF M， AYACHI R， SAID Y， et al. An evaluation of retinanet on indoor object detection for blind and visually impaired persons assistance navigation［J］. Neural Processing Letters， 2020，51（3）：2265-2279.
［4］ AFIF M， AYACHI R， PISSALOUX E， et al. Indoor objects detection and recognition for an ICT mobility assistance of visually impaired people［J］. Multimedia Tools and Applications， 2020，79（41-42）：31645-31662.
［5］ LOPEZ-CIFUENTES A， ESCUDERO-VI[N]OLO M， BESC
OS J， et al. Semantic-aware scene recognition［J］. Pattern Recognition， 2020，102. DOI： 10.1016/j.patcog.2020.107256.
［6］ KHAN A， CHEFRANOV A， DEMIREL H. Building discriminative features of scene recognition using multi-stages of inception-ResNet-v2［J］. Applied Intelligence， 2023，53（15）：18431-18449.
［7］ ZHANG L H， LI L Q， PAN X P， et al. Multi-level ensemble network for scene recognition［J］. Multimedia Tools and Applications， 2019，78（19）：28209-28230.
［8］ TANG P J， WANG H L， KWONG S. G-MS2F： GoogleNet based multi-stage feature fusion of deep CNN for scene recognition［J］. Neurocomputing， 2017，225：188-197.
［9］ Simonyan K， Zisserman A. Very deep convolutional networks for large-scale image recognition［J］// arXiv preprint arXiv: 1409.1556，2014.
［10］ SZEGEDY C， LIU W， JIA Y Q， et al. Going deeper with convolutions［C］// 2015 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2015：1-9.
［11］ HE K M， ZHANG X Y， REN S Q， et al. Deep residual learning for image recognition［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2016：770-778.
［12］ HUANG G， LIU Z， VAN DER MAATEN L， et al. Densely connected convolutional networks［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE，2017：2261-2269.
［13］ WOO S， PARK J， LEEJY， et al. CBAM： Convolutional block attention module［C］// Proceedings of the 2018 European Conference on Computer Vision（ECCV）Springer，2018：3-19.
［14］ WANG C， PENG G H， DE BAETS B. Deep feature fusion through adaptive discriminative metric learning for scene recognition［J］. Information Fusion， 2020，63：1-12.
［15］ SANDLER M， HOWARD A， ZHU M L， et al. Inverted residuals and linear bottleneck：Mobile networks for classification，detection and segmentation［J］. arXiv preprint arXiv：1801.04381，2018.
［16］ ZHANG X Y， ZHOU X Y， LIN M X， et al. ShuffleNet： An extremely efficient convolutional neural network for mobile devices［C］// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2018：6848-6856.
［17］ TAN M X， LE Q V. EfficientNet： Rethinking model scaling for convolutional neural networks［C］// Proceedings of the 36th International Conference on Machine Learning. PMLR， 2019：6105-6114.
［18］ HAN K， WANG Y H， TIAN Q， et al. GhostNet： More features from cheap operations［C］// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2020：1577-1586.
［19］ MEHTA S， RASTEGARI M， CASPI A， et al. ESPNet： Efficient spatial pyramid of dilated convolutions for semantic segmentation［C］// 2018 European Conference on Computer Vision. Springer， 2018：561-580.
［20］ ZHAO H S， SHI J P， QI X J， et al. Pyramid scene parsing network［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2017：6230-6239.
［21］ HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// 2018 IEEE Conference on Computer Vision and Pattem Recognition， IEEE， 2018： 7132-7141.
［22］ WANG Q L， WU B G， ZHU P F， et al. ECA-Net： Efficient channel attention for deep convolutional neural networks［C］// 2020 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2020：11531-11539.
［23］ FANG Y W， CAI Y X， CHEN J T， et al. Cross-layer retrospective retrieving via layer attention［J］. arXiv preprint arXiv：2302.03985， 2023.
［24］ QUATTONI A， TORRALBA A. Recognizing indoor scenes［C］// 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEEE， 2009：413-420.
［25］ LI F F， PERONA P. A Bayesian hierarchical model for learning natural scene categories［C］// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE， 2005：524-531.
［26］ XIE G S， ZHANG X Y， YAN S C， et al．Hybrid CNN and dictionary-based models for scene recognition and domain adaption［J］. IEEE Transaction on Circuits & Systems for Video Technology， 2017，27（6）：1263-1274.
［27］ WANG L M， GUO S， HUANG W L， et al. Knowledge guided disambiguation for large-scale scene classification with multi-resolution CNNs［J］. Computer Vision and Pattern Recognition， 2017，26（4）：2055-2068.
［28］ WANG Z， WANG L M， WANG Y L， et al. Weakly supervised patchnets： Describing and aggregating local patches for scene recognition［J］. IEEE Transactions on Image Processing， 2017，26（4）：2028-2041.

[1]	武丽1, 张征浩2, 葛彩成2, 俞俊2. 基于改进SCNN网络的车道线检测算法[J]. 计算机与现代化, 2024, 0(07): 87-92.
[2]	周超, 丛鑫, 訾玲玲, 肖谷平. 基于DNN与注意力机制的推荐算法模型[J]. 计算机与现代化, 2024, 0(06): 1-7.
[3]	袁世一. 基于经验模态分解与极限学习机的粮食产量模型预测[J]. 计算机与现代化, 2024, 0(03): 47-53.
[4]	周永钦, 王勇, 王瑛. 基于多尺度特征及注意力机制的轻量化PCB缺陷检测方法#br#[J]. 计算机与现代化, 2024, 0(02): 88-92.
[5]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[6]	李延满, 王必恒, 赵羚焱. 基于轻量化YOLOv5的安全帽检测[J]. 计算机与现代化, 2023, 0(10): 59-64.
[7]	刘禅奕, 黄丹, 薛林雁, 王涛, 朱桃, . 改进EfficientNet网络的COVID-19 X光分类[J]. 计算机与现代化, 2023, 0(09): 94-99.
[8]	殷远齐, 徐源, 邢远新. 基于YOLO v4的车辆目标检测算法[J]. 计算机与现代化, 2022, 0(07): 8-14.