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

## TL;DR

This paper introduces fast and accurate methods for estimating human body joint positions from single depth images using random forest techniques.

## Contribution

The paper proposes four novel forest walk algorithms for real-time human pose estimation from depth images.

## Key findings

- The proposed methods achieve higher accuracy than current state-of-the-art techniques.
- They operate efficiently with a significant advantage in computation time.
- Accurate 3D joint positions are inferred without needing temporal prior information.

## 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.