Title:
路上障害物検知装置、路上障害物検知方法、及び路上障害物検知プログラム
Document Type and Number:
Japanese Patent JP7310718
Kind Code:
B2
Abstract:
An on-road obstacle detection device that includes: a memory; and a processor, the processor being connected to the memory and being configured to: assign a semantic label to each pixel in an image using a first discriminator that has been pre-trained using images in which an on-road obstacle is not present; and detect an on-road obstacle based on a probability density of the semantic label assigned.
Inventors:
Masao Yamanaka
Application Number:
JP2020092676A
Publication Date:
July 19, 2023
Filing Date:
May 27, 2020
Export Citation:
Assignee:
Toyota Motor Corporation
International Classes:
G08G1/00; G06T7/00; G06T7/11; G08G1/16
Domestic Patent References:
| JP2019211900A | ||||
| JP2018194912A |
Other References:
Krzysztof Lis et al.,"Detecting the Unexpected via Image Resynthesis",2019 IEEE/CVF International Conference on Computer Vision (ICCV),米国,IEEE,2019年10月27日,pp.2152-2161
Vijay Badrinarayanan et al.,"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation",IEEE Transactions on Pattern Analysis and Machine Intelligence,米国,IEEE,2017年01月02日,Vol.39, No.12,pp.2481-2495
尾▲崎▼ 信之,“車載向け画像・認識技術動向 ~Viscontiでの事例を踏まえて~”,映像情報メディア学会誌,日本,一般社団法人映像情報メディア学会,2019年11月01日,Vol.73, No.6,pp.48-54
Vijay Badrinarayanan et al.,"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation",IEEE Transactions on Pattern Analysis and Machine Intelligence,米国,IEEE,2017年01月02日,Vol.39, No.12,pp.2481-2495
尾▲崎▼ 信之,“車載向け画像・認識技術動向 ~Viscontiでの事例を踏まえて~”,映像情報メディア学会誌,日本,一般社団法人映像情報メディア学会,2019年11月01日,Vol.73, No.6,pp.48-54
Attorney, Agent or Firm:
Patent Attorney Corporation Taiyo International Patent Office