Simultaneous egomotion estimation, segmentation, and moving object detection

Abstract

Robust egomotion estimation is a key prerequisite for making a robot truly autonomous. In previous work, a multimodel extension of random sample consensus (RANSAC) was introduced to deal with environments with rapid changes by incorporating moving object information. A multiscale matching algorithm was also proposed to resolve the issue of imperfect segmentation. In this paper, we present a novel specialization of RANSAC that extends the previous work. A unified framework is introduced to achieve simultaneously egomotion estimation, multiscale segmentation, and moving object detection in the RANSAC paradigm. The motivation of this work is to provide a robust real-time solution to the problem of egomotion estimation, segmentation, and moving object detection in highly dynamic environments. The idea is to augment the discriminative power of spatial and temporal appearances of objects by the spatiotemporal consistency. The objective is twofold. First, split mismerged segments and distinguish nonstationary objects from stationary objects by the spatial consistency. Second, merge oversegmented segments and differentiate moving objects from outlying objects by the temporal consistency. Moving objects of considerably different sizes, from pedestrians to trucks, can be properly segmented and correctly detected. We also show that the performance of egomotion estimation can be further improved by taking into account both stationary and moving object information. Our approach is extensively evaluated on challenging data sets and compared to the state of the art. The experiments also show that our approach serves as a general framework that works well with various planar range data. C 2011 Wiley Periodicals, Inc.

A segmentation and data association annotation system for laser-based multi-target tracking evaluation

“…It has been shown that the state-of-the-art MTT algorithms perform well in general cases [13][14] [15]. Accordingly, our first design is to run a good MTT algorithm to generate segmentation and data association results automatically.…”

Ambient motion estimation in dynamic scenes using wearable visual-inertial sensors

“…Remark 1 (Recoverability): Uniform rectilinear ambient motion is recoverable from visual optical flows when ego dynamics are involved and measured. The optical flows resulted by ambient motion on a stable observer is modeled in (3). It is infeasible to recover absolute scales of translational speeds due to the coupling between depths and translational motion.…”

“…Estimation of ambient motion using limited onboard or wearable sensors is a fundamental challenge in application of intelligent robots and assistive devices [1], [2], [3]. Increasing robotic applications require a robot to work in complex and dynamic environments with limited prior knowledge [4].…”

2D LiDAR Map Prediction via Estimating Motion Flow with GRU

“…Then, the next map can be predicted. Following this framework, some methods [4], [5], [6] aim at tackling the general motion of arbitrary types of objects. However, this problem is too complicated for traditional methods, and the performance is unsatisfying.…”

“…Then, the next map can be predicted by estimating the state of moving objects. To this end, traditional methods [1], [2], [3], [4], [5], [6] usually divide the pipeline into several steps, 1 including to detect separate objects, associate measurements with tracked objects, estimate the state, and predict the next state of each tracked object. Then, the next map can be predicted.…”