Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Context

Greer, Ross; Gopalkrishnan, Akshay; Deo, Nachiket; Rangesh, Akshay; Trivedi, Mohan M.

doi:10.48550/arxiv.2301.05804

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(via a limited number of deformable attention heads) where an image should be sampled to extract meaningful relational features to the region of interest. As defined in [8], this approach is known as the Deformable Detection Transformer, described in technical detail in the following section.…”

Section: A Overviewmentioning

confidence: 99%

“…We propose that salience-aware training methods can be used to improve the training of traffic light detection systems. We make two contributions: (1) creation of the first salienceannotated LAVA Salient Lights Dataset, and (2) using the concept of Salience-Sensitive Focus Loss defined in [8], evaluation of the impact of Salience-Sensitive Focal Loss while training detection transformer models.…”

Section: B Saliencementioning

confidence: 99%

“…Instead, using a supervised learning process, Greer et al [9] classify the saliency of road signs, which can be utilized for efficient dataset annotation. This led to the LAVA Salient Signs Dataset [8], a dataset of 31,191 labeled traffic signs with a validated salience property. Lateef et al [24] utilize a conditional GAN that predicts the important things a driver should be looking at within a traffic scene, matching the definition we use for instructive salience.…”

Section: Traffic Object Salience Researchmentioning

confidence: 99%

See 2 more Smart Citations

On Salience-Sensitive Sign Classification in Autonomous Vehicle Path Planning: Experimental Explorations with a Novel Dataset

Greer

Isa

Deo

et al. 2022

2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

View full text Add to dashboard Cite

One of the most important tasks for ensuring safe autonomous driving systems is accurately detecting road traffic lights and accurately determining how they impact the driver's actions. In various real-world driving situations, a scene may have numerous traffic lights with varying levels of relevance to the driver, and thus, distinguishing and detecting the lights that are relevant to the driver and influence the driver's actions is a critical safety task. This paper proposes a traffic light detection model which focuses on this task by first defining salient lights as the lights that affect the driver's future decisions. We then use this salience property to construct the LAVA Salient Lights Dataset, the first US traffic light dataset with an annotated salience property. Subsequently, we train a Deformable DETR object detection transformer model using Salience-Sensitive Focal Loss to emphasize stronger performance on salient traffic lights, showing that a model trained with this loss function has stronger recall than one trained without.

show abstract

Section: A Overviewmentioning

confidence: 99%

Section: B Saliencementioning

confidence: 99%