Priors for Stereo Vision under Adverse Weather Conditions

Gehrig, Stefan; Reznitskii, Maxim; Schneider, Nicolai; Franke, Uwe; Weickert, Joachim

doi:10.1109/iccvw.2013.39

Cited by 17 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In regions with low contrast or with high sensor noise, most implementations have difficulties. However, specific implementations allow 3D perception also in adverse weather like rain [ 85 , 114 , 115 ]. This result can be achieved by exploiting stereo confidence clues based in a probabilistic implementation (a Bayesian manner) of scene and temporal priors (prior knowledge of scene instants before) for the improvement of the stereo matching.…”

Section: Discussionmentioning

confidence: 99%

Motorcycles that See: Multifocal Stereo Vision Sensor for Advanced Safety Systems in Tilting Vehicles

Gil

Savino

Piantini

et al. 2018

Sensors

View full text Add to dashboard Cite

Advanced driver assistance systems, ADAS, have shown the possibility to anticipate crash accidents and effectively assist road users in critical traffic situations. This is not the case for motorcyclists, in fact ADAS for motorcycles are still barely developed. Our aim was to study a camera-based sensor for the application of preventive safety in tilting vehicles. We identified two road conflict situations for which automotive remote sensors installed in a tilting vehicle are likely to fail in the identification of critical obstacles. Accordingly, we set two experiments conducted in real traffic conditions to test our stereo vision sensor. Our promising results support the application of this type of sensors for advanced motorcycle safety applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Motorcycles that See: Multifocal Stereo Vision Sensor for Advanced Safety Systems in Tilting Vehicles

Gil

Savino

Piantini

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…It turns out that the number of false positives is reduced significantly, whereas the detection rate of obstacles increases. In comparison to our state of the art stereo techniques [10], [11], the approach achieves the best performance on this data set. By leveraging an efficient NVIDIA CUDA framework, our algorithm runs in real-time in our test vehicle, requiring less than 10 ms per frame.…”

Section: Introductionmentioning

confidence: 74%

“…• Stixels with confidences (StixConf ): Results of the Stixel World using SGM stereo with confidence estimation as described in [10]. • Stixels with temporal stereo scene priors (StixScenePrior): Results of the Stixel World using stereo which is based on a graph-cut technique with temporal scene priors [11]. Note that no stereo confidences (and therefore no Stixel confidences) are available.…”

Section: Realization Of the Framework And Technical Detailsmentioning

confidence: 99%

Stix-Fusion: A Probabilistic Stixel Integration Technique

Muffert

Schneider

Franke

2014

2014 Canadian Conference on Computer and Robot Vision

Self Cite

View full text Add to dashboard Cite

In summer 2013, a Mercedes S-Class drove completely autonomously for about 100 km from Mannheim to Pforzheim, Germany, using only close-to-production sensors. In this project, called Mercedes Benz Intelligent Drive, stereo vision was one of the main sensing components. For the representation of free space and obstacles we relied on the so called Stixel World, a generic 3D intermediate representation which is computed from dense disparity images.In spite of the high performance of the Stixel World in most common traffic scenes, the availability of this technique is limited. For instance under adverse weather, rain or even spray water on the windshield results in erroneous disparity images which generate false Stixel results. This can lead to undesired behavior of autonomous vehicles.Our goal is to use the Stixel World for a robust free space estimation and a reliable obstacle detection even during difficult weather conditions.In this paper, we meet this challenge and fuse the Stixels incrementally into a reference grid map. Our new approach is formulated in a Bayesian manner and is based on existence estimation methods. We evaluate our new technique on a manually labeled database with emphasis on bad weather scenarios. The number of structures which are detected mistakenly within free space areas is reduced by a factor of two whereas the detection rate of obstacles increases at the same time.

show abstract

“…Garg and Nayar (2007),Siegwart et al (2011), Henry et al (2012,Samadzadegan et al (2011),Wang et al (2013),Gehrig et al (2013),Mossel (2015),Akai et al (2016), Guan et al (2016), Rivero et al (2017) Sonar HC -SR04 HRLV -MaxSonar -EZ Least affected by rain, smoke, dust, etc. as compared to laser and vision sensor Martí et al (2012), Santos et al (2015), Papa et al (2016), Siciliano and Khatib (2016), Zaffar et al (2018)…”

mentioning

confidence: 99%

Comparative analysis of range sensors for the robust autonomous navigation – a review

Singh

Nagla

2019

View full text Add to dashboard Cite

Purpose The purpose of this research is to provide the necessarily and resourceful information regarding range sensors to select the best fit sensor for robust autonomous navigation. Autonomous navigation is an emerging segment in the field of mobile robot in which the mobile robot navigates in the environment with high level of autonomy by lacking human interactions. Sensor-based perception is a prevailing aspect in the autonomous navigation of mobile robot along with localization and path planning. Various range sensors are used to get the efficient perception of the environment, but selecting the best-fit sensor to solve the navigation problem is still a vital assignment. Design/methodology/approach Autonomous navigation relies on the sensory information of various sensors, and each sensor relies on various operational parameters/characteristic for the reliable functioning. A simple strategy shown in this proposed study to select the best-fit sensor based on various parameters such as environment, 2 D/3D navigation, accuracy, speed, environmental conditions, etc. for the reliable autonomous navigation of a mobile robot. Findings This paper provides a comparative analysis for the diverse range sensors used in mobile robotics with respect to various aspects such as accuracy, computational load, 2D/3D navigation, environmental conditions, etc. to opt the best-fit sensors for achieving robust navigation of autonomous mobile robot. Originality/value This paper provides a straightforward platform for the researchers to select the best range sensor for the diverse robotics application.

show abstract

Priors for Stereo Vision under Adverse Weather Conditions

Cited by 17 publications

References 32 publications

Motorcycles that See: Multifocal Stereo Vision Sensor for Advanced Safety Systems in Tilting Vehicles

Motorcycles that See: Multifocal Stereo Vision Sensor for Advanced Safety Systems in Tilting Vehicles

Stix-Fusion: A Probabilistic Stixel Integration Technique

Comparative analysis of range sensors for the robust autonomous navigation – a review

Contact Info

Product

Resources

About