Near Zone Pedestrian Detection using a Low-Resolution FIR Sensor

Källhammer, Jan-Erik; Eriksson, Dick; Granlund, Gösta H.; Felsberg, Michael; Moe, Anders; Johansson, Björn; Wiklund, Johan; Forssén, Per-Erik

doi:10.1109/ivs.2007.4290137

Cited by 10 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We should also note that monocular SaM has an inherent scale ambiguity [1]. Despite this, the estimated structure can still be effectively used for obstacle avoidance if time-to-collision is used as the metric [8].The main contributions of this paper are:1. Introduction of a distance constraint that significantly reduces the number of RANSAC iterations in the five point algorithm, while retaining the pose accuracy.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Fast and Accurate Structure and Motion Estimation

Hedborg

Forssén

Felsberg

2009

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. This paper describes a system for structure-and-motion estimation for real-time navigation and obstacle avoidance. We demonstrate a technique to increase the efficiency of the 5-point solution to the relative pose problem. This is achieved by a novel sampling scheme, where we add a distance constraint on the sampled points inside the RANSAC loop, before calculating the 5-point solution. Our setup uses the KLT tracker to establish point correspondences across time in live video. We also demonstrate how an early outlier rejection in the tracker improves performance in scenes with plenty of occlusions. This outlier rejection scheme is well suited to implementation on graphics hardware. We evaluate the proposed algorithms using real camera sequences with fine-tuned bundle adjusted data as ground truth. To strenghten our results we also evaluate using sequences generated by a state-of-the-art rendering software. On average we are able to reduce the number of RANSAC iterations by half and thereby double the speed.Structure and motion (SaM) estimation from video sequences is a well explored subject [1][2][3]. The underlying mathematics is well understood, see e.g. [1], and commercial systems, such as Boujou by 2d3 [4], are used in the movie industry on a regular basis. Current research challenges involve making such systems faster, more accurate, and more robust, see e.g. [2,3]. These issues are far from solved, as is illustrated by the 2007 DARPA urban challenge [5]. In the end, none of the finalists chose to use the vision parts of their systems, instead they relied soley on LIDAR to obtain 3D structure. Clearly there is still work to be done in the field. This paper aims to increase the speed and accuracy in structure-and-motion estimation for an autonomous system with a forward looking camera, see figure 1. Although on a smaller scale, this platform has the same basic geometry and motion patterns as the DARPA contenders, and as the vision based collision warning systems developed for automotive applications. In such systems, estimated 3D structure can be used to detect obstacles and navigable surfaces.When dealing with forward motion there are a number of problems that must be adressed. The effective baseline is on average much smaller than for the sideways motion case, resulting in a more noise sensitive structure estimation. A tracked point feature near the camera often has a short lifespan because it 2 Johan Hedborg, Per-Erik Forssén, and Michael Felsberg quickly moves out of the the visual field. Unfortunately, such points also contain most of the structural information [6]. Forward motion also produces large scale changes in some parts of the image, and this can be a problem for some trackers.This paper studies the calibrated SaM formulation, which has several advantages over the uncalibrated formulation. In calibrated SaM, estimated cameras and structure will be in Euclidean space instead of a projective space, and we can use more constrained problem formulations [1]. Planar-dominant scenes are not ...

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Fast and Accurate Structure and Motion Estimation

Hedborg

Forssén

Felsberg

2009

Advances in Visual Computing

View full text Add to dashboard Cite

show abstract

“…Using a thermal sensor with low spatial resolution, [28] builds a robust pedestrian detector by combining three different methods. [19] also proposes a low resolution system for pedestrian detection from vehicles. [32] proposes a pedestrian detection system that detects people based on their temperature and dimensions, and tracks them using a Kalman filter.…”

Section: Related Workmentioning

confidence: 99%

Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery

Gade

Jorgensen

Moeslund

2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

102

View full text Add to dashboard Cite

“…Consequently, pedestrians and other warmer objects like vehicle undersides are imaged at brighter intensities. We follow the initial pedestrian detection approach in [14] by first selecting interesting regions by scanning for hot-spots in the image. The interesting regions found by the hot-spot detector provide seeds to an energy minimization based pedestrian model fitting algorithm which detects pedestrian aspect ROIs as initial detections.…”

Section: Pedestrian Detection and Appearance Matchingmentioning

confidence: 99%

Pedestrian localization by appearance matching and multi-mode filtering

Wu¹,

Bansal²,

Eledath³

2009

2009 IEEE Intelligent Vehicles Symposium

View full text Add to dashboard Cite

This paper addresses the frame-to-frame data association and state estimation problems in localization of a pedestrian relative to a moving vehicle from a far infra-red video sequence. In a novel application of the hierarchical modelbased motion estimation framework, we are able to solve the frame-to-frame data association problem as well as estimate a sub-pixel accurate height ratio for a pedestrian in two frames. To estimate the position and velocity of a pedestrian, instead of using a constant pedestrian height model, we propose a novel approach of using the interacting multiple-hypothesismode/height filtering algorithm. We present a method to calculate the probability of each mode from the estimated and measured pedestrian height ratios in images. These mode probabilities are then used to accurately estimate the pedestrian location by combining the mode based estimations. We demonstrate the effectiveness of our approach comparing it to a constant height model based approach on several IR sequences.

show abstract

Near Zone Pedestrian Detection using a Low-Resolution FIR Sensor

Cited by 10 publications

References 12 publications

Fast and Accurate Structure and Motion Estimation

Fast and Accurate Structure and Motion Estimation

Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery

Pedestrian localization by appearance matching and multi-mode filtering

Contact Info

Product

Resources

About