Limits...
Forest Walk Methods for Localizing Body Joints from Single Depth Image.

Jung HY, Lee S, Heo YS, Yun ID - PLoS ONE (2015)

Bottom Line: A regression forest is trained to estimate the probability distribution to the direction or offset toward the particular joint, relative to the adjacent position.The distribution for next position is found from traversing the regression tree from new position.The continual position sampling through 3D space will eventually produce an expectation of sample positions, which we estimate as the joint position.

View Article: PubMed Central - PubMed

Affiliation: Division of Computer and Electronic Systems Engineering, Hankuk University of Foreign Studies, Yongin, Republic of Korea.

ABSTRACT
We present multiple random forest methods for human pose estimation from single depth images that can operate in very high frame rate. We introduce four algorithms: random forest walk, greedy forest walk, random forest jumps, and greedy forest jumps. The proposed approaches can accurately infer the 3D positions of body joints without additional information such as temporal prior. A regression forest is trained to estimate the probability distribution to the direction or offset toward the particular joint, relative to the adjacent position. During pose estimation, the new position is chosen from a set of representative directions or offsets. The distribution for next position is found from traversing the regression tree from new position. The continual position sampling through 3D space will eventually produce an expectation of sample positions, which we estimate as the joint position. The experiments show that the accuracy is higher than current state-of-the-art pose estimation methods with additional advantage in computation time.

No MeSH data available.


Related in: MedlinePlus

(a) mAP of RTW with varying step numbers and sizes for the EVAL sequence. (b) mAP of GTW with varying step numbers and sizes for the EVAL sequence. In (a) and (b), each line represents different step sizes.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4581738&req=5

pone.0138328.g004: (a) mAP of RTW with varying step numbers and sizes for the EVAL sequence. (b) mAP of GTW with varying step numbers and sizes for the EVAL sequence. In (a) and (b), each line represents different step sizes.

Mentions: Different step sizes have different saturation numbers. If each step is large, the targeted joint position will be reached quickly, provided that the direction selections are mostly correct. If the step size is too large, however, the steps may keep jumping over the correct joint position, and it might step into a new position where it cannot find correct direction toward the target joint. For random and greedy walk using a single tree, the step sizes were varied among 2 cm, 5 cm, 10 cm, and 20 cm in the evaluation as presented in Fig 4. The mAP for different step size and number of steps are tested for the EVAL set. The number of steps are varied from 8, 16, 32, 64, 128, and 256.


Forest Walk Methods for Localizing Body Joints from Single Depth Image.

Jung HY, Lee S, Heo YS, Yun ID - PLoS ONE (2015)

(a) mAP of RTW with varying step numbers and sizes for the EVAL sequence. (b) mAP of GTW with varying step numbers and sizes for the EVAL sequence. In (a) and (b), each line represents different step sizes.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4581738&req=5

pone.0138328.g004: (a) mAP of RTW with varying step numbers and sizes for the EVAL sequence. (b) mAP of GTW with varying step numbers and sizes for the EVAL sequence. In (a) and (b), each line represents different step sizes.
Mentions: Different step sizes have different saturation numbers. If each step is large, the targeted joint position will be reached quickly, provided that the direction selections are mostly correct. If the step size is too large, however, the steps may keep jumping over the correct joint position, and it might step into a new position where it cannot find correct direction toward the target joint. For random and greedy walk using a single tree, the step sizes were varied among 2 cm, 5 cm, 10 cm, and 20 cm in the evaluation as presented in Fig 4. The mAP for different step size and number of steps are tested for the EVAL set. The number of steps are varied from 8, 16, 32, 64, 128, and 256.

Bottom Line: A regression forest is trained to estimate the probability distribution to the direction or offset toward the particular joint, relative to the adjacent position.The distribution for next position is found from traversing the regression tree from new position.The continual position sampling through 3D space will eventually produce an expectation of sample positions, which we estimate as the joint position.

View Article: PubMed Central - PubMed

Affiliation: Division of Computer and Electronic Systems Engineering, Hankuk University of Foreign Studies, Yongin, Republic of Korea.

ABSTRACT
We present multiple random forest methods for human pose estimation from single depth images that can operate in very high frame rate. We introduce four algorithms: random forest walk, greedy forest walk, random forest jumps, and greedy forest jumps. The proposed approaches can accurately infer the 3D positions of body joints without additional information such as temporal prior. A regression forest is trained to estimate the probability distribution to the direction or offset toward the particular joint, relative to the adjacent position. During pose estimation, the new position is chosen from a set of representative directions or offsets. The distribution for next position is found from traversing the regression tree from new position. The continual position sampling through 3D space will eventually produce an expectation of sample positions, which we estimate as the joint position. The experiments show that the accuracy is higher than current state-of-the-art pose estimation methods with additional advantage in computation time.

No MeSH data available.


Related in: MedlinePlus