Fusion of 3D-LIDAR and camera data for scene parsing

Zhao, Gangqiang; Xiao, Xuhong; Yuan, Junsong; Ng, Gee Wah

doi:10.1016/j.jvcir.2013.06.008

Cited by 61 publications

(45 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach provides a finer representation of the environment, but at the expense of increased processing time and reduced memory efficiency. To mitigate this, usually a voxel-based filtering mechanism is applied to the raw point cloud to reduce the number of points, e.g., [24,25].…”

Section: Representationmentioning

confidence: 99%

“…In [24,27,32,49,50], the authors implemented the RANSAC algorithm to segment the ground plane in the point cloud with the assumption of flat surface. However, as mentioned in [23,51], for non-planar surfaces, such as undulated roads, uphill, downhill, and humps, this model fitting method is not adequate.…”

Section: Segmentation Algorithmsmentioning

confidence: 99%

“…x n = x n−1 u 1 (24) where x represents state variable, and u represents input to the system. The problem can be further simplified as a single input system by assigning the first control input u 1 to be a function of time.…”

Section: Trajectory Tracking With a Modelmentioning

confidence: 99%

See 2 more Smart Citations

Perception, Planning, Control, and Coordination for Autonomous Vehicles

et al. 2017

View full text Add to dashboard Cite

Autonomous vehicles are expected to play a key role in the future of urban transportation systems, as they offer potential for additional safety, increased productivity, greater accessibility, better road efficiency, and positive impact on the environment. Research in autonomous systems has seen dramatic advances in recent years, due to the increases in available computing power and reduced cost in sensing and computing technologies, resulting in maturing technological readiness level of fully autonomous vehicles. The objective of this paper is to provide a general overview of the recent developments in the realm of autonomous vehicle software systems. Fundamental components of autonomous vehicle software are reviewed, and recent developments in each area are discussed.

show abstract

Section: Representationmentioning

confidence: 99%

Section: Segmentation Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Perception, Planning, Control, and Coordination for Autonomous Vehicles

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Besides the study of segmenting 3D point clouds [22], researchers have also started working on fusion based scene parsing. They often conduct segmentation on an image and a 3D point cloud individually, while paying attention to integrating two segmentation results via fusion techniques such as the fuzzy logic inference framework [23].…”

Section: Related Workmentioning

confidence: 99%

Road scene segmentation via fusing camera and lidar data

Huang

Gong

Xiang

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

This paper presents an approach for pixel-wise object segmentation for road scenes based on the integration of a color image and an aligned 3D point cloud. In light of the advantage of range information in object discovery, we first produce initial object hypotheses by clustering the sparse 3D point cloud. The image pixels registered to the clustered 3D points are taken as samples to learn each object's prior knowledge. The priors are represented by Gaussian Mixture Models (GMMs) of color and 3D location information only, requiring no high-level features. We further formulate the segmentation problem within a Conditional Random Field (CRF) framework, which incorporates the learned prior models, together with hard constraints placed on the registered pixels and pairwise spatial constraints to achieve final results. Our algorithm is validated on the challenging KITTI dataset which contains diverse complicated road scenarios. Both qualitative and quantitative evaluation results show the superiority of our algorithm.

show abstract

“…The above-mentioned appearance and geometric features are extracted to classify each grid into traversable or non-traversable categories. The other method fuses multi-modalities at decision level [12]. Specifically, it classifies each sensor's data individually and then combines the classification results by a fusion scheme.…”

Section: Introductionmentioning

confidence: 99%

Integrating visual and range data for road detection

Huang

Gong

Liu

2013

2013 IEEE International Conference on Image Processing

View full text Add to dashboard Cite

This paper presents a new method for detecting drivable road surfaces in a single image. The method takes advantage of range and visual information so that reliable results are achieved. Specifically, given LIDAR data and an aligned image, it first makes use of 3D points to estimate the ground plane and determine the horizon. Then, subsets of road and obstacle points are extracted from the 3D points based on the plane and LIDAR properties. The pixels registered to the extracted points are used to build apriori road and non-road appearance models. The road detection problem is further formulated using Markov random field whose energy function is defined based on the learned models. Constraints are also added on the energy function to place high confidence on the pixels that are registered to extracted 3D points. Extensive experiments on urban roads and highways show that our method is robust even in complicated environments.

show abstract

Fusion of 3D-LIDAR and camera data for scene parsing

Cited by 61 publications

References 34 publications

Perception, Planning, Control, and Coordination for Autonomous Vehicles

Perception, Planning, Control, and Coordination for Autonomous Vehicles

Road scene segmentation via fusing camera and lidar data

Integrating visual and range data for road detection

Contact Info

Product

Resources

About