| Full text | |
| Author(s): |
Tokuda, Eric K.
;
Ferreira, Gabriel B. A.
;
Silva, Claudio
;
Cesar-, Roberto M., Jr.
;
IEEE
Total Authors: 5
|
| Document type: | Journal article |
| Source: | 2018 IEEE SOUTHWEST SYMPOSIUM ON IMAGE ANALYSIS AND INTERPRETATION (SSIAI); v. N/A, p. 4-pg., 2018-01-01. |
| Abstract | |
In this work we propose a semi-supervised learning approach for object detection where we use detections from a preexisting detector to train a new detector. We differ from previous works by coming up with a relative quality metric which involves simpler labeling and by proposing a full framework of automatic generation of improved detectors. To validate our method, we collected a comprehensive dataset of more than two thousand hours of streaming from public traffic cameras that contemplates variations in time, location and weather. We used these data to generate and assess with weak labeling a car detector that outperforms popular detectors on hard situations such as rainy weather and low resolution images. Experimental results are reported, thus corroborating the relevance of the proposed approach. (AU) | |
| FAPESP's process: | 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery |
| Grantee: | Roberto Marcondes Cesar Junior |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 16/12077-6 - Data-driven city model representation and analysis using visual and non-visual information |
| Grantee: | Eric Keiji Tokuda |
| Support Opportunities: | Scholarships abroad - Research Internship - Doctorate |
| FAPESP's process: | 14/24918-0 - Weakly supervised learning for face and person attributes detection |
| Grantee: | Eric Keiji Tokuda |
| Support Opportunities: | Scholarships in Brazil - Doctorate |
| FAPESP's process: | 15/03475-5 - Watching the cities: big data and computer vision for analysis of urban environments |
| Grantee: | Gabriel Augusto Bianchi Azevedo Ferreira |
| Support Opportunities: | Scholarships in Brazil - Scientific Initiation |