Presentation 2020-12-17
Vehicle detection using visualization of deep learning from in-vehicle night-time camera image
Tatsuya Oyabu, Gosuke Ohashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have been working on vehicle detection at night-time using deep learning. In general, the burden of creating correct labels for object detection is enormous compared to image classification. Therefore, we study a method for predicting the presence of vehicle on the road based on vehicle lights from the visualization results of image classification, which has a low cost of creating correct labels. In the conventional visualization methods, it is difficult to visualize small areas. Therefore, we propose a method inspired from the structure of an object detection model to visualize the task-driven small area in the scene.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep Learning / Vehicle Detection / Visualization / Classification
Paper # PRMU2020-50
Date of Issue 2020-12-10 (PRMU)

Conference Information
Committee PRMU
Conference Date 2020/12/17(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Transfer learning and few shot learning
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.)
Secretary Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.)
Assistant Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Vehicle detection using visualization of deep learning from in-vehicle night-time camera image
Sub Title (in English)
Keyword(1) Deep Learning
Keyword(2) Vehicle Detection
Keyword(3) Visualization
Keyword(4) Classification
1st Author's Name Tatsuya Oyabu
1st Author's Affiliation Shizuoka University(Shizuoka Univ.)
2nd Author's Name Gosuke Ohashi
2nd Author's Affiliation Shizuoka University(Shizuoka Univ.)
Date 2020-12-17
Paper # PRMU2020-50
Volume (vol) vol.120
Number (no) PRMU-300
Page pp.pp.69-74(PRMU),
#Pages 6
Date of Issue 2020-12-10 (PRMU)