Title:
CLASS-SENSITIVE EDGE DETECTION METHOD BASED ON DEEP LEARNING
Document Type and Number:
WIPO Patent Application WO/2020/119624
Kind Code:
A1
Abstract:
A class-sensitive edge detection method based on deep learning. A deep learning neural network model is used to obtain edge classification detection results of several class targets. A deep supervision method is used for model training. Labels for adaptive scale transformation are used during a training process. A loss function of a reset weight and a general cross-loss entropy function are used intersectingly. By employing the present method, specific target edges may be detected and the obtained edges may be classified at the same time. Compared to existing deep learning edge detection methods, the present invention not only improves the detection accuracy, but also obtains more detailed image edges while requiring little subsequent reprocessing. In addition, functions have been expanded, which may provide better performance guarantee for other tasks which have edges as the basis, such as target segmentation and instance segmentation.
More Like This:
Inventors:
WANG LEI (CN)
XU CHENGJUN (CN)
CHENG JUN (CN)
XU CHENGJUN (CN)
CHENG JUN (CN)
Application Number:
PCT/CN2019/123968
Publication Date:
June 18, 2020
Filing Date:
December 09, 2019
Export Citation:
Assignee:
SHENZHEN INST OF ADV TECH CAS (CN)
International Classes:
G06T7/13
Domestic Patent References:
| WO2018023734A1 | 2018-02-08 |
Foreign References:
| CN109741351A | 2019-05-10 | |||
| CN108710919A | 2018-10-26 |
Other References:
YU, ZHIDING ET AL.: "CASENet: Deep Category-Aware Semantic Edge Detection", 2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 31 December 2017 (2017-12-31), XP033249517, DOI: 20200303111926X
Attorney, Agent or Firm:
BEIJING CHENGHUI LAW FIRM (CN)
Download PDF: