Hyunggic !
-
Research :
Multi-Sensor Fusion for Moving Object Detection and Tracking :
DPMs for Urban Object Recognition :
Motorcyclist DPM
Motorcyclist DPM
Introduction
This motorcyclist DPM was designed and trained especially for autototive active safety applications such as FCW (Forward Collision Warning).
We collected vehicle dataset in various places and weather conditions. It consists of one training sets (set00) and one testing sets (set01), each with 2 seq files, along with associated annotation files. Due to our purpose, most of samples corresponds to rear view samples of motorcycles. The dataset was very carefully collected based on our investigation about vehicle accident statistics [1]. So, we believe that this dataset could be very valuable for those safety applications.
[1] National Motor Vehicle Crash Casusation Survey
NHTSA, 2008
[Typical Samples with annotations]
[Dataset Statistics]
Left pie chart shows the distribution of vehicle samples and right hand figure shows the distribution of bottom lines of all (i.e., 5,276) bounding boxes. Key numbers are:
Motorcycle_rear: 4,927
Motorcycle_front: 85
Motorcycle_right: 3
Motorcycle_left: 27
Top row shows a height distribution and bottom row shows ratio distribution of each sub-type.
[Trained Motorcyclist Model: Rear (4,927) / Side (30) / Diagonal (234)]
[Result Video]
Motorcyclist detection result on Pittsburgh Dataset