Abstract | ||
---|---|---|
An accurate and efficient method for obstacle detection is a key component of a robotic navigation system. Concerning indoor environments, the ground surface can be modeled as a plane (or a set of) and once estimated it can be employed for obstacle detection, e.g. points lying above and below are considered obstacles. The same does not hold for off-road and urban scenarios where one cannot expect planar surfaces or obvious structural patterns. In 2002, Talukder et al. presented a method to deal with such environments. Their method is based on the height difference and "slope" between three-dimensional points. Despite having been used successfully on several occasions, the method has a high computational cost. We propose the use of a Graphics Processing Unit (GPU) to enable its execution in real time. Experiments were performed using a stereo camera and an RGB-D sensor, where the GPU implementation has been compared to multi-core and single-core CPU implementations. The results reveal a significant gain in computational performance, reaching a speedup of almost 80 times in a specific instance. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/IVS.2013.6629630 | 2013 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV) |
Keywords | Field | DocType |
stereo camera,kernel,mobile robots,multicore processing | Stereo camera,Obstacle,Object detection,Computer science,Navigation system,Real-time computing,Computational science,Point cloud,Graphics processing unit,Multi-core processor,Speedup | Conference |
ISSN | Citations | PageRank |
1931-0587 | 2 | 0.40 |
References | Authors | |
3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Caio César Teodoro Mendes | 1 | 22 | 1.71 |
Fernando Santos Osório | 2 | 114 | 19.08 |
Denis Fernando Wolf | 3 | 47 | 9.86 |