Segmentation and recognition using structure from motion point clouds

We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3D world structure that vary with object category. We introduce features that project the 3D cues back to the 2D image plane while modeling spatial layout and context. A randomized decision forest combines many such features to achieve a coherent 2D segmentation and recognize the object categories present. Our main contribution is to show how semantic segmentation is possible based solely on motion-derived 3D world structure. Our method works well on sparse, noisy point clouds, and unlike existing approaches, does not need appearance-based descriptors. Experiments were performed on a challenging new video database containing sequences filmed from a moving car in daylight and at dusk. The results confirm that indeed, accurate segmentation and recognition are possible using only motion and 3D world structure. Further, we show that the motion-derived information complements an existing state-of-the-art appearance-based method, improving both qualitative and quantitative performance. © 2008 Springer Berlin Heidelberg.

Semi-supervised video segmentation using tree structured graphical models

We present a novel, implementation friendly and occlusion aware semi-supervised video segmentation algorithm using tree structured graphical models, which delivers pixel labels alongwith their uncertainty estimates. Our motivation to employ supervision is to tackle a task-specific segmentation problem where the semantic objects are pre-defined by the user. The video model we propose for this problem is based on a tree structured approximation of a patch based undirected mixture model, which includes a novel time-series and a soft label Random Forest classifier participating in a feedback mechanism. We demonstrate the efficacy of our model in cutting out foreground objects and multi-class segmentation problems in lengthy and complex road scene sequences. Our results have wide applicability, including harvesting labelled video data for training discriminative models, shape/pose/articulation learning and large scale statistical analysis to develop priors for video segmentation. © 2011 IEEE.

Initializing Vision Based Trackers Using Semantic Texton Forests

Vision based tracking can provide the spatial location of project related entities such as equipment, workers, and materials in a large-scale congested construction site. It tracks entities in a video stream by inferring their motion. To initiate the process, it is required to determine the pixel areas of the entities to be tracked in the following consecutive video frames. For the purpose of fully automating the process, this paper presents an automated way of initializing trackers using Semantic Texton Forests (STFs) method. STFs method performs simultaneously the segmentation of the image and the classification of the segments based on the low-level semantic information and the context information. In this paper, STFs method is tested in the case of wheel loaders recognition. In the experiments, wheel loaders are further divided into several parts such as wheels and body parts to help learn the context information. The results show 79% accuracy of recognizing the pixel areas of the wheel loader. These results signify that STFs method has the potential to automate the initialization process of vision based tracking.