Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning

Milz, Stefan; Arbeiter, Georg; Witt, Christian; Abdallah, Bassam; Yogamani, Senthil

doi:10.1109/cvprw.2018.00062

Cited by 98 publications

(49 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Menze et al [25] running time is 50 minutes per frame which makes it impossible for usage in a real-time application such as the autonomous driving. Deep learning algorithms are becoming successful beyond object detection [30] for applications like visual SLAM [26], depth estimation [17], soiling detection [33] but it is still relatively less explored for MOD task.…”

Section: Related Workmentioning

confidence: 99%

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

Rashed

Ramzy

Vaquero

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

Moving object detection is a critical task for autonomous vehicles. As dynamic objects represent higher collision risk than static ones, our own ego-trajectories have to be planned attending to the future states of the moving elements of the scene. Motion can be perceived using temporal information such as optical flow. Conventional optical flow computation is based on camera sensors only, which makes it prone to failure in conditions with low illumination. On the other hand, LiDAR sensors are independent of illumination, as they measure the time-of-flight of their own emitted lasers. In this work, we propose a robust and real-time CNN architecture for Moving Object Detection (MOD) under low-light conditions by capturing motion information from both camera and LiDAR sensors. We demonstrate the impact of our algorithm on KITTI dataset where we simulate a low-light environment creating a novel dataset "Dark-KITTI". We obtain a 10.1% relative improvement on Dark-KITTI, and a 4.25% improvement on standard KITTI relative to our baselines. The proposed algorithm runs at 18 fps on a standard desktop GPU using 256 × 1224 resolution images.

show abstract

Section: Related Workmentioning

confidence: 99%

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

Rashed

Ramzy

Vaquero

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The objective of the FGO is to minimize the summation of the residual function (20) to approach the optimal states set . Unfortunately, the non-linear function (20) is always a non-convex problem that has multiple sub-optimal, the local minimums.…”

Section: Adaptive M-estimatormentioning

confidence: 99%

“…The smaller is k (black curve in Figure 7), the milder is the curve and the more robust it is meanwhile. However, a k with too smaller value can lead to an extremely small gradient of the error function (20), making the optimizer difficult to approach the optimal state. The researches in [33,34] show that extensive parameter tuning is required to obtain satisfactory performance using M-estimator.…”

Section: Adaptive M-estimatormentioning

confidence: 99%

“…The straight forward method to mitigate the effects of dynamic objects is to detect and remove the features belong to the dynamic objects from visual simultaneous localization and mapping (SLAM) [20,21]. Due to the many dynamic objects in complex environments, a detect-SLAM system [22] is proposed to integrate SLAM with a deep neural network to detect the moving objects and remove the unreliable features from moving objects.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Visual-Inertial Integrated Navigation System Aided by Online Sensor Model Adaption for Autonomous Ground Vehicles in Urban Areas

Bai

Wen

Hsu

2020

Preprint

View full text Add to dashboard Cite

Visual-inertial integrated navigation system (VINS) has been extensively studied over the past decades to provide accurate and low-cost positioning solutions for autonomous systems. Satisfactory performance can be obtained in an ideal scenario with sufficient and static environment features. However, there are usually numerous dynamic objects in deep urban areas, and these moving objects can severely distort the feature tracking process which is fatal to the feature-based VINS. The well-known method mitigates the effects of dynamic objects is to detect the vehicles using deep neural networks and remove the features belongs to the surrounding vehicle. However, excessive exclusion of features can severely distort the geometry of feature distribution, leading to limited visual measurements. Instead of directly eliminating the features from dynamic objects, this paper proposes to adopt the visual measurement model based on the quality of feature tracking to improve the performance of VINS. Firstly, a self-tuning covariance estimation approach is proposed to model the uncertainty of each feature measurements by integrating two parts: 1) the geometry of feature distribution (GFD), 2) the quality of feature tracking. Secondly, an adaptive M-estimator is proposed to correct the measurement residual model to further mitigate the impacts of outlier measurements, such as the dynamic features. Different from the conventional M-estimator, the proposed method effectively alleviates the reliance of excessive parameterization of M-estimator. Experiments are conducted in a typical urban area of Hong Kong with numerous dynamic objects, and the results show that the proposed method could effectively mitigate the effects of dynamic objects and improved accuracy of VINS is obtained when compared with the conventional method.

show abstract

“…The other fast developing area of forefront road identification is based on image processing from monocular and binocular (stereo) cameras for using the extracted data in Advanced Driving Assistance Systems (ADAS) (Krasner, Katz 2016;Prashanth et al 2014) or self-driving vehicle systems (Yang et al 2018;Mahmud et al 2012;Milz et al 2018). Monocular vision is usually used for determining weather and illumination (Gimonet et al 2015;Cheng et al 2018), path and obstacle (Nadav, Katz 2016), road, line, road edge detection and recognition (Yang et al 2018;Van Hamme et al 2013;Zhang, Wu 2009).…”

Section: System Adaptation In Advancementioning

confidence: 99%

Technological Measures of Forefront Road Identification for Vehicle Comfort and Safety Improvement

2019

View full text Add to dashboard Cite

This paper presents the technological measures currently being developed at institutes and vehicle research centres dealing with forefront road identification. In this case, road identification corresponds with the surface irregularities and road surface type, which are evaluated by laser scanning and image analysis. Real-time adaptation, adaptation in advance and system external informing are stated as sequential generations of vehicle suspension and active braking systems where road identification is significantly important. Active and semi-active suspensions with their adaptation technologies for comfort and road holding characteristics are analysed. Also, an active braking system such as Anti-lock Braking System (ABS) and Autonomous Emergency Braking (AEB) have been considered as very sensitive to the road friction state. Artificial intelligence methods of deep learning have been presented as a promising image analysis method for classification of 12 different road surface types. Concluding the achieved benefit of road identification for traffic safety improvement is presented with reference to analysed research reports and assumptions made after the initial evaluation.

show abstract

Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning

Cited by 98 publications

References 40 publications

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

FuseMODNet: Real-Time Camera and LiDAR Based Moving Object Detection for Robust Low-Light Autonomous Driving

Robust Visual-Inertial Integrated Navigation System Aided by Online Sensor Model Adaption for Autonomous Ground Vehicles in Urban Areas

Technological Measures of Forefront Road Identification for Vehicle Comfort and Safety Improvement

Contact Info

Product

Resources

About