Real-time semantic segmentation based on improved BiSeNet

نویسندگان

چکیده

ä¸ºäº†æå‡å›¾åƒè¯­ä¹‰åˆ†å‰²ç®—æ³•çš„æ€§èƒ½ï¼Œä½¿å ¶åŒæ—¶æ»¡è¶³å‡†ç¡®æ€§å’Œå®žæ—¶æ€§éœ€æ±‚ï¼Œæœ¬æ–‡æå‡ºäº†ä¸€ç§åŸºäºŽæ”¹è¿›BiSeNetçš„å®žæ—¶å›¾åƒè¯­ä¹‰åˆ†å‰²ç®—æ³•ã€‚é¦–å ˆï¼Œé€šè¿‡ä½¿åŒåˆ†æ”¯ç½‘ç»œå¤´éƒ¨å ±äº«ä»¥æ¶ˆé™¤BiSeNetç½‘ç»œç»“æž„éƒ¨åˆ†é€šé“å’Œå‚æ•°çš„å†—ä½™ï¼ŒåŒæ—¶æœ‰æ•ˆæå–å›¾åƒçš„æµ å±‚ç‰¹å¾ï¼›ç„¶åŽï¼Œå°†ä¸Šè¿°å ±äº«ç½‘ç»œæ‹†åˆ†ä¸ºç”±ç»†èŠ‚åˆ†æ”¯å’Œè¯­ä¹‰åˆ†æ”¯ç»„æˆçš„åŒåˆ†æ”¯ç½‘ç»œï¼Œå¹¶åˆ†åˆ«ç”¨äºŽæå–ç©ºé—´ç»†èŠ‚ä¿¡æ¯å’Œè¯­ä¹‰ä¸Šä¸‹æ–‡ä¿¡æ¯ï¼›æ­¤å¤–ï¼Œåœ¨è¯­ä¹‰åˆ†æ”¯å°¾éƒ¨å¼•å ¥é€šé“å’Œç©ºé—´æ³¨æ„åŠ›æœºåˆ¶ä»¥å¢žå¼ºç‰¹å¾è¡¨è¾¾èƒ½åŠ›ï¼Œé€šè¿‡ä½¿ç”¨åŒæ³¨æ„åŠ›æœºåˆ¶å¯¹BiSeNetç®—æ³•è¿›è¡Œä¼˜åŒ–ä»¥æ›´æœ‰æ•ˆåœ°æå–è¯­ä¹‰ä¸Šä¸‹æ–‡ç‰¹å¾ï¼›æœ€åŽï¼Œå¯¹ç»†èŠ‚åˆ†æ”¯å’Œè¯­ä¹‰åˆ†æ”¯çš„ç‰¹å¾è¿›è¡Œèžåˆå¹¶é€šè¿‡ä¸Šé‡‡æ ·æ“ä½œæ¢å¤è‡³è¾“å ¥å›¾åƒåˆ†è¾¨çŽ‡å¤§å°ä»¥å®žçŽ°å›¾åƒè¯­ä¹‰åˆ†å‰²ã€‚æœ¬æ–‡ç®—æ³•åœ¨Cityscapes数据集以95.3FPS的实时性表现达到77.2% mIoU的准确性;在CamVid数据集以179.1 FPS的实时性表现达到73.8% mIoUçš„å‡†ç¡®æ€§ã€‚å®žéªŒç»“æžœè¡¨æ˜Žï¼Œæœ¬æ–‡ç®—æ³•åœ¨å®žæ—¶æ€§å’Œå‡†ç¡®æ€§æ–¹é¢èŽ·å¾—äº†å¾ˆå¥½çš„å¹³è¡¡ï¼Œå ¶è¯­ä¹‰åˆ†å‰²æ€§èƒ½ç›¸è¾ƒäºŽBiSeNetç®—æ³•åŠå ¶å®ƒçŽ°æœ‰ç®—æ³•å¾—åˆ°äº†æ˜¾è‘—çš„æå‡ã€‚

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Real-Time Semantic Clothing Segmentation

Clothing segmentation is a challenging field of research which is rapidly gaining attention. This paper presents a system for semantic segmentation of primarily monochromatic clothing and printed/stitched textures in single images or live video. This is especially appealing to emerging augmented reality applications such as retexturing sports players’ shirts with localized adverts or statistics...

متن کامل

Real-Time Semantic Segmentation Benchmarking Framework

Semantic segmentation has major benefits in autonomous driving and robotics related applications, where scene understanding is a necessity. Most of the research on semantic segmentation is focused on increasing the accuracy of segmentation models with few research on real-time performance. The few work conducted in this direction does not also provide principled methods to evaluate the differen...

متن کامل

ShuffleSeg: Real-time Semantic Segmentation Network

Real-time semantic segmentation is of significant importance for mobile and robotics related applications. We propose a computationally efficient segmentation network which we term as ShuffleSeg. The proposed architecture is based on grouped convolution and channel shuffling in its encoder for improving the performance. An ablation study of different decoding methods is compared including Skip ...

متن کامل

Real-Time Semantic Segmentation with Label Propagation

Despite of the success of convolutional neural networks for semantic image segmentation, CNNs cannot be used for many applications due to limited computational resources. Even efficient approaches based on random forests are not efficient enough for real-time performance in some cases. In this work, we propose an approach based on superpixels and label propagation that reduces the runtime of a ...

متن کامل

RTSeg: Real-time Semantic Segmentation Comparative Study

Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally efficient solutions. The few work conducted in this direction does not provide principled methods to evaluate the different design choices for segmentation. In ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Guangxue jingmi gongcheng

سال: 2023

ISSN: ['1004-924X']

DOI: https://doi.org/10.37188/ope.20233108.1217