Safety-Aware Hardening of 3D Object Detection Neural Network Systems
- URL: http://arxiv.org/abs/2003.11242v3
- Date: Wed, 1 Apr 2020 09:46:22 GMT
- Title: Safety-Aware Hardening of 3D Object Detection Neural Network Systems
- Authors: Chih-Hong Cheng
- Abstract summary: We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware.
The concept is detailed by extending the state-of-the-art PIXOR detector which creates object bounding boxes in bird's eye view with inputs from point clouds.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study how state-of-the-art neural networks for 3D object detection using a
single-stage pipeline can be made safety aware. We start with the safety
specification (reflecting the capability of other components) that partitions
the 3D input space by criticality, where the critical area employs a separate
criterion on robustness under perturbation, quality of bounding boxes, and the
tolerance over false negatives demonstrated on the training set. In the
architecture design, we consider symbolic error propagation to allow
feature-level perturbation. Subsequently, we introduce a specialized loss
function reflecting (1) the safety specification, (2) the use of single-stage
detection architecture, and finally, (3) the characterization of robustness
under perturbation. We also replace the commonly seen non-max-suppression
post-processing algorithm by a safety-aware non-max-inclusion algorithm, in
order to maintain the safety claim created by the neural network. The concept
is detailed by extending the state-of-the-art PIXOR detector which creates
object bounding boxes in bird's eye view with inputs from point clouds.
Related papers
- Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation [9.578322021478426]
3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving.
Existing methods critically overlook the inherent vulnerability to real-world perturbations (e.g., snow, fog, rain) and adversarial distortions.
This work first identifies two intrinsic limitations that undermine current PCSS-UDA robustness.
We propose a tripartite framework consisting of: 1) a robustness evaluation model quantifying resilience against adversarial attack/corruption types through robustness metrics; 2) an invertible attention alignment module (IAAM) enabling bidirectional domain mapping while preserving discriminative structure via attention-guided overlap suppression; and
arXiv Detail & Related papers (2025-04-02T12:16:23Z) - Online Collision Risk Estimation via Monocular Depth-Aware Object Detectors and Fuzzy Inference [6.856508678236828]
The framework takes two sets of predictions produced by different algorithms and associates their inconsistencies with the collision risk via fuzzy inference.
We experimentally validate that, based on Intersection-over-Union (IoU) and a depth discrepancy measure, the inconsistencies between the two sets of predictions strongly correlate to the safety-related error of the 3D object detector.
arXiv Detail & Related papers (2024-11-09T20:20:36Z) - Uncertainty Estimation for 3D Object Detection via Evidential Learning [63.61283174146648]
We introduce a framework for quantifying uncertainty in 3D object detection by leveraging an evidential learning loss on Bird's Eye View representations in the 3D detector.
We demonstrate both the efficacy and importance of these uncertainty estimates on identifying out-of-distribution scenes, poorly localized objects, and missing (false negative) detections.
arXiv Detail & Related papers (2024-10-31T13:13:32Z) - Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation Patterns [12.384452095533396]
Integrity monitoring of automated driving systems (ADS) is paramount for ensuring safety.
Recent advancements in deep neural network (DNN)-based object detectors, their susceptibility to detection errors remains a significant concern.
arXiv Detail & Related papers (2024-04-11T12:24:47Z) - LS-VOS: Identifying Outliers in 3D Object Detections Using Latent Space
Virtual Outlier Synthesis [10.920640666237833]
LiDAR-based 3D object detectors have achieved unprecedented speed and accuracy in autonomous driving applications.
They are often biased toward high-confidence predictions or return detections where no real object is present.
We propose LS-VOS, a framework for identifying outliers in 3D object detections.
arXiv Detail & Related papers (2023-10-02T07:44:26Z) - OriCon3D: Effective 3D Object Detection using Orientation and Confidence [0.0]
We propose an advanced methodology for the detection of 3D objects from a single image.
We use a deep convolutional neural network-based 3D object weighted orientation regression paradigm.
Our approach significantly improves the accuracy of 3D object pose determination, surpassing baseline methodologies.
arXiv Detail & Related papers (2023-04-27T19:52:47Z) - Uncertainty-Aware AB3DMOT by Variational 3D Object Detection [74.8441634948334]
Uncertainty estimation is an effective tool to provide statistically accurate predictions.
In this paper, we propose a Variational Neural Network-based TANet 3D object detector to generate 3D object detections with uncertainty.
arXiv Detail & Related papers (2023-02-12T14:30:03Z) - Geometry of Radial Basis Neural Networks for Safety Biased Approximation
of Unsafe Regions [15.933842803733244]
This manuscript describes the specific geometry of the neural network used for zeroing barrier function synthesis.
It shows how the network provides the necessary representation for splitting the state space into safe and unsafe regions.
arXiv Detail & Related papers (2022-10-11T16:34:42Z) - Self-Supervised Masked Convolutional Transformer Block for Anomaly
Detection [122.4894940892536]
We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level.
In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
arXiv Detail & Related papers (2022-09-25T04:56:10Z) - AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
We propose a novel 3D detection framework that associates intact features for objects via domain adaptation.
We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
arXiv Detail & Related papers (2022-08-24T16:54:38Z) - Anchor-free 3D Single Stage Detector with Mask-Guided Attention for
Point Cloud [79.39041453836793]
We develop a novel single-stage 3D detector for point clouds in an anchor-free manner.
We overcome this by converting the voxel-based sparse 3D feature volumes into the sparse 2D feature maps.
We propose an IoU-based detection confidence re-calibration scheme to improve the correlation between the detection confidence score and the accuracy of the bounding box regression.
arXiv Detail & Related papers (2021-08-08T13:42:13Z) - Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for
Online Collision Avoidance [95.86944752753564]
We propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties.
Our algorithm combines an object detection pipeline with a recurrent neural network (RNN) which infers the covariance of state estimates.
The robustness of our methods is validated on complex quadruped robot dynamics and can be generally applied to most robotic platforms.
arXiv Detail & Related papers (2020-07-28T07:34:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.