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

The adjacent joint positions can be used as the starting positions for new RTW.(a) illustrates the kinematic tree implemented along with RTW. First, the random walk toward belly positions starts from body center. The belly positions (red dot in (a)) become starting point for hips and chest, and so forth. (b) shows the RTW path examples.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0138328.g002: The adjacent joint positions can be used as the starting positions for new RTW.(a) illustrates the kinematic tree implemented along with RTW. First, the random walk toward belly positions starts from body center. The belly positions (red dot in (a)) become starting point for hips and chest, and so forth. (b) shows the RTW path examples.

Mentions: For localizing problems, a regression tree can be trained for relative offset to the target joint position as in [10] and [36]. Otherwise, a correct position can be found if the direction toward the position is known in any point on the body. Ideally, the directions or offsets to all parts should be trained from all possible positions in the whole body. This will ensure the correct joint position to be found even when starting from a random point as shown in Fig 1. However, this is difficult to train and heavily redundant. Rather, a kinematic tree can be used to reduce the size of regions required for training and to provide a nearby starting point for an adjacent joint such that all position samples are approximately in-line with the skeletal frame. See Fig 2. Details of the method are provided in the following subsections, starting with training sample collection.


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

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

The adjacent joint positions can be used as the starting positions for new RTW.(a) illustrates the kinematic tree implemented along with RTW. First, the random walk toward belly positions starts from body center. The belly positions (red dot in (a)) become starting point for hips and chest, and so forth. (b) shows the RTW path examples.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0138328.g002: The adjacent joint positions can be used as the starting positions for new RTW.(a) illustrates the kinematic tree implemented along with RTW. First, the random walk toward belly positions starts from body center. The belly positions (red dot in (a)) become starting point for hips and chest, and so forth. (b) shows the RTW path examples.
Mentions: For localizing problems, a regression tree can be trained for relative offset to the target joint position as in [10] and [36]. Otherwise, a correct position can be found if the direction toward the position is known in any point on the body. Ideally, the directions or offsets to all parts should be trained from all possible positions in the whole body. This will ensure the correct joint position to be found even when starting from a random point as shown in Fig 1. However, this is difficult to train and heavily redundant. Rather, a kinematic tree can be used to reduce the size of regions required for training and to provide a nearby starting point for an adjacent joint such that all position samples are approximately in-line with the skeletal frame. See Fig 2. Details of the method are provided in the following subsections, starting with training sample collection.

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