Corpus ID: 236456455

RGB cameras failures and their effects in autonomous driving applications

  title={RGB cameras failures and their effects in autonomous driving applications},
  author={Francesco Secci and Andrea Ceccarelli},
RGB cameras are one of the most relevant sensors for autonomous driving applications. It is undeniable that failures of vehicle cameras may compromise the autonomous driving task, possibly leading to unsafe behaviors when images that are subsequently processed by the driving system are altered. To support the definition of safe and robust vehicle architectures and intelligent systems, in this paper we define the failure modes of a vehicle camera, together with an analysis of effects and known… Expand


On failures of RGB cameras and their effects in autonomous driving applications
This paper defines the failure modes of a vehicle camera together with an analysis of effects and known mitigations, and builds a software library for the generation of the corresponding failed images and feeds them to the trained agent of an autonomous driving simulator. Expand
End to End Vehicle Lateral Control Using a Single Fisheye Camera
A novel model to generate this data and label augmentation using only one short range fisheye camera is presented and how it can be used as a consistent metric for lateral end-to-end control evaluation is presented. Expand
Are we ready for autonomous driving? The KITTI vision benchmark suite
The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Expand
Remote Attacks on Automated Vehicles Sensors : Experiments on Camera and LiDAR
This paper presents remote attacks on camera-based system and LiDAR using commodity hardware and proposes software and hardware countermeasures that improve sensors resilience against these attacks. Expand
RGB-D Object Classification for Autonomous Driving Perception
Autonomous driving systems (ADS) comprise, essentially, sensory perception (including AI-ML-based techniques), localization, decision-making, and control. The cornerstone of an ADS is the sensoryExpand
Approaching Camera-based Real-World Navigation Using Object Recognition
It is argued that object recognition is essential for a navigation system to generalize learned landmarks to new driving scenes, which is a requirement for practical driving and an online learning neural network for indoor navigation is presented. Expand
Wide-angle camera technology for automotive applications: a review
The development of electronic vision systems for the automotive market is a strongly growing field, driven in particular by customer demand to increase the safety of vehicles both for drivers and forExpand
Can You Trust Autonomous Vehicles : Contactless Attacks against Sensors of Self-driving Vehicle
To improve road safety and driving experiences, autonomous vehicles have emerged recently, and they can sense their surroundings and navigate without human intervention. Although promising andExpand
Object scene flow for autonomous vehicles
A novel model and dataset for 3D scene flow estimation with an application to autonomous driving by representing each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object. Expand
Benchmarking Image Sensors Under Adverse Weather Conditions for Autonomous Driving
This work describes a testing and evaluation methodology that helps to benchmark novel sensor technologies and compare them to state-of-the-art sensors and it is shown that gated imaging outperforms state- of theart standard passive imaging due to time-synchronized active illumination. Expand