کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
4947530 | 1439585 | 2017 | 22 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Class-specific object proposals re-ranking for object detection in automatic driving
ترجمه فارسی عنوان
پیشنهادهای شیء خاص کلاس برای تشخیص شی در رانندگی خودکار دوباره رتبه بندی می شود
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
رتبه بندی مجدد پیشنهاد شی، تشخیص شی، سی ان ان،
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
چکیده انگلیسی
Object proposal generation is an important step in object detection, obtaining high-quality proposals can effectively improve the performance of detection. In this paper, we propose a semantic, class-specific approach to re-rank object proposals, which can consistently improve the recall performance even with fewer proposals. Specifically, we first extract features for each proposal including semantic segmentation, stereo information, contextual information, CNN-based objectness and low-level cue, and then score them using class-specific weights learned by Structured SVM. The advantages of the proposed model are two-fold: 1) it can be easily merged to existing generators with few computational costs, and 2) it can achieve high recall rate under strict critical even using fewer proposals. Experimental evaluation on the KITTI benchmark demonstrates that our approach significantly improves existing popular generators on recall performance. Moreover, in the experiment conducted for object detection, even with 1500 proposals, our approach can still have higher average precision (AP) than baselines with 5000 proposals.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 242, 14 June 2017, Pages 187-194
Journal: Neurocomputing - Volume 242, 14 June 2017, Pages 187-194
نویسندگان
Zhun Zhong, Mingyi Lei, Donglin Cao, Jianping Fan, Shaozi Li,