Direct Visual Localisation and Calibration for Road Vehicles in Changing City Environments

Pascoe, Geoffrey; Maddern, William; Newman, Paul

doi:10.1109/iccvw.2015.23

Cited by 45 publications

(29 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The intensities of a camera image and a synthetic image can also be matched by probabilistic metrics (Pascoe et al, 2015;Taylor & Nieto, 2012;Wang, Ferrie, & Macfarlane, 2012). These metrics are functions of the marginal and the joint probabilities, where the joint probability is acquired from the pixel-to-pixel correspondence.…”

Section: Related Workmentioning

confidence: 99%

Automatic targetless camera–LIDAR calibration by aligning edge with Gaussian mixture model

Kang

Doh

2019

Journal of Field Robotics

View full text Add to dashboard Cite

This paper presents a calibration algorithm that does not require an artificial target object to precisely estimate a rigid‐body transformation between a camera and a light detection and ranging (LIDAR) sensor. The proposed algorithm estimates calibration parameters by minimizing a cost function that evaluates the edge alignment between two sensor measurements. In particular, the proposed cost function is constructed using a projection model‐based many‐to‐many correspondence of the edges to fully exploit measurements with different densities (dense photometry and sparse geometry). The alignment of the many‐to‐many correspondence is represented using the Gaussian mixture model (GMM) framework. Here, each component of the GMM, including weight, displacement, and standard deviation, is derived to suitably capture the intensity, location, and influential range of the edge measurements, respectively. The derived cost function is optimized by the gradient descent method with an analytical derivative. A coarse‐to‐fine scheme is also applied by gradually decreasing the standard deviation of the GMM to enhance the robustness of the algorithm. Extensive indoor and outdoor experiments validate the claim that the proposed GMM strategy improves the performance of the proposed algorithm. The experimental results also show that the proposed algorithm outperforms previous methods in terms of precision and accuracy by providing calibration parameters of standard deviations less than 0.6° and 2.1 cm with a reprojection error of 1.78 for a 2.1‐megapixel image (2,048 × 1,024) in the best case.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic targetless camera–LIDAR calibration by aligning edge with Gaussian mixture model

Kang

Doh

2019

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…This approach effectively identifies obstacles the vehicle may collide with even in the presence of pitching and rolling motions. The camera-LIDAR calibration G CL for the RobotCar vehicle was determined using the method in [34]; for the AnnieWAY vehicle the calibration provided with the KITTI Raw dataset was used.…”

Section: A Platform Specificationsmentioning

confidence: 99%

Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy

Barnes

Maddern

Posner

2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

105

View full text Add to dashboard Cite

We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our proposed method generates vast quantities of labelled images containing proposed paths and obstacles without requiring manual annotation, which we then use to train a deep semantic segmentation network. With the trained network we can segment proposed paths and obstacles at run-time using a vehicle equipped with only a monocular camera without relying on explicit modelling of road or lane markings. We evaluate our method on the largescale KITTI and Oxford RobotCar datasets and demonstrate reliable path proposal and obstacle segmentation in a wide variety of environments under a range of lighting, weather and traffic conditions. We illustrate how the method can generalise to multiple path proposals at intersections and outline plans to incorporate the system into a framework for autonomous urban driving.

show abstract

“…At a frequency of about 15 Hz each camera takes an RGB image with resolution 1024×768. Although it is possible to use this raw image data directly [14], it is somewhat complicated. A more common approach is to condense the image into a set of feature points with associated descriptor vector, and view this as the measurement.…”

Section: A Observationsmentioning

confidence: 99%

Long-Term Visual Localization Using Semantically Segmented Images

Stenborg

Toft

Hammarstrand

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

118

View full text Add to dashboard Cite

Robust cross-seasonal localization is one of the major challenges in long-term visual navigation of autonomous vehicles. In this paper, we exploit recent advances in semantic segmentation of images, i.e., where each pixel is assigned a label related to the type of object it represents, to attack the problem of long-term visual localization. We show that semantically labeled 3D point maps of the environment, together with semantically segmented images, can be efficiently used for vehicle localization without the need for detailed feature descriptors (SIFT, SURF, etc.). Thus, instead of depending on hand-crafted feature descriptors, we rely on the training of an image segmenter. The resulting map takes up much less storage space compared to a traditional descriptor based map. A particle filter based semantic localization solution is compared to one based on SIFT-features, and even with large seasonal variations over the year we perform on par with the larger and more descriptive SIFT-features, and are able to localize with an error below 1 m most of the time.

show abstract

Direct Visual Localisation and Calibration for Road Vehicles in Changing City Environments

Cited by 45 publications

References 27 publications

Automatic targetless camera–LIDAR calibration by aligning edge with Gaussian mixture model

Automatic targetless camera–LIDAR calibration by aligning edge with Gaussian mixture model

Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy

Long-Term Visual Localization Using Semantically Segmented Images

Contact Info

Product

Resources

About