# Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification

Source: [Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification](<https://www.sota2.com/research/paper/68fa74d81e209131cea641cb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:19:27.756Z

Authors: Marin Ka\\v{c}an, Marko \\v{S}evrovi\\'c, Sini\\v{s}a \\v{S}egvi\\'c

Published: 2022-11-08T11:10:07.000Z

## Abstract

Road-safety inspection is an indispensable instrument for reducing road-accident fatalities contributed to road infrastructure. Recent work formalizes road-safety assessment in terms of carefully selected risk factors that are also known as road-safety attributes. In current practice, these attributes are manually annotated in geo-referenced monocular video for each road segment. We propose to reduce dependency on tedious human labor by automating recognition with a two-stage neural architecture. The first stage predicts more than forty road-safety attributes by observing a local spatio-temporal context. Our design leverages an efficient convolutional pipeline, which benefits from pre-training on semantic segmentation of street scenes. The second stage enhances predictions through sequential integration across a larger temporal window. Our design leverages per-attribute instances of a lightweight bidirectional LSTM architecture. Both stages alleviate extreme class imbalance by incorporating a multi-task variant of recall-based dynamic loss weighting. We perform experiments on the iRAP-BH dataset, which involves fully labeled geo-referenced video along 2,300 km of public roads in Bosnia and Herzegovina. We also validate our approach by comparing it with the related work on two road-scene classification datasets from the literature: Honda Scenes and FM3m. Experimental evaluation confirms the value of our contributions on all three datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.04165>)

[PDF](<https://arxiv.org/pdf/2211.04165.pdf>)
