Project/Area Number |
24800032
|
Research Category |
Grant-in-Aid for Research Activity Start-up
|
Allocation Type | Single-year Grants |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | Toyohashi University of Technology |
Principal Investigator |
JINNO Takao 豊橋技術科学大学, 工学(系)研究科(研究院), 助教 (10636070)
|
Project Period (FY) |
2012-08-31 – 2014-03-31
|
Project Status |
Completed (Fiscal Year 2013)
|
Budget Amount *help |
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2012: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
Keywords | HDR符号化 / トーンマッピング / 多層符号化 / 物体追跡 / 傷検出 / HDR画像 / 傷検知 / グレースケール化 |
Research Abstract |
High dynamic range (HDR) images have more details than conventional images therefore it is expected to apply to object detection, object tracking or flaw detection. Most of multi-layer HDR coding techniques, however, cannot achieve both improving accuracy of them and high coding efficiency. This research proposed invertible tone-mapping technique which can improve the accuracy of SIFT object tracking. We achieved a high efficient multi-layer HDR coding by using invertibility of tone-mapping, and it can selectively decode two types of tone-mapping effects: edge-preserving smoothing effect for object detection and detail enhancement effect for object tracking.
|