V-RoAst: A New Dataset for Visual Road Assessment

Road traffic crashes cause millions of deaths annually and have a significant economic impact, particularly in low- and middle-income countries (LMICs). This paper presents an approach using Vision Language Models (VLMs) for road safety assessment, overcoming the limitations of traditional Convolutional Neural Networks (CNNs). We introduce a new task ,V-RoAst (Visual question answering for Road Assessment), with a real-world dataset. Our approach optimizes prompt engineering and evaluates advanced VLMs, including Gemini-1.5-flash and GPT-4o-mini. The models effectively examine attributes for road assessment. Using crowdsourced imagery from Mapillary, our scalable solution influentially estimates road safety levels. In addition, this approach is designed for local stakeholders who lack resources, as it does not require training data. It offers a cost-effective and automated methods for global road safety assessments, potentially saving lives and reducing economic burdens.

SMA-Hyper: Spatiotemporal Multi-View Fusion Hypergraph Learning for Traffic Accident Prediction

Predicting traffic accidents is the key to sustainable city management, which requires effective address of the dynamic and complex spatiotemporal characteristics of cities. Current data-driven models often struggle with data sparsity and typically overlook the integration of diverse urban data sources and the high-order dependencies within them. Additionally, they frequently rely on predefined topologies or weights, limiting their adaptability in spatiotemporal predictions. To address these issues, we introduce the Spatiotemporal Multiview Adaptive HyperGraph Learning (SMA-Hyper) model, a dynamic deep learning framework designed for traffic accident prediction. Building on previous research, this innovative model incorporates dual adaptive spatiotemporal graph learning mechanisms that enable high-order cross-regional learning through hypergraphs and dynamic adaptation to evolving urban data. It also utilises contrastive learning to enhance global and local data representations in sparse datasets and employs an advance attention mechanism to fuse multiple views of accident data and urban functional features, thereby enriching the contextual understanding of risk factors. Extensive testing on the London traffic accident dataset demonstrates that the SMA-Hyper model significantly outperforms baseline models across various temporal horizons and multistep outputs, affirming the effectiveness of its multiview fusion and adaptive learning strategies. The interpretability of the results further underscores its potential to improve urban traffic management and safety by leveraging complex spatiotemporal urban data, offering a scalable framework adaptable to diverse urban environments.

Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis

Panoramic cycling videos can record 360{\deg} views around the cyclists. Thus, it is essential to conduct automatic road user analysis on them using computer vision models to provide data for studies on cycling safety. However, the features of panoramic data such as severe distortions, large number of small objects and boundary continuity have brought great challenges to the existing CV models, including poor performance and evaluation methods that are no longer applicable. In addition, due to the lack of data with annotations, it is not easy to re-train the models. In response to these problems, the project proposed and implemented a three-step methodology: (1) improve the prediction performance of the pre-trained object detection models on panoramic data by projecting the original image into 4 perspective sub-images; (2) introduce supports for boundary continuity and category information into DeepSORT, a commonly used multiple object tracking model, and set an improved detection model as its detector; (3) using the tracking results, develop an application for detecting the overtaking behaviour of the surrounding vehicles. Evaluated on the panoramic cycling dataset built by the project, the proposed methodology improves the average precision of YOLO v5m6 and Faster RCNN-FPN under any input resolution setting. In addition, it raises MOTA and IDF1 of DeepSORT by 7.6\% and 9.7\% respectively. When detecting the overtakes in the test videos, it achieves the F-score of 0.88. The code is available on GitHub at github.com/cuppp1998/360_object_tracking to ensure the reproducibility and further improvements of results.

Quantifying Geospatial in the Common Crawl Corpus

Large language models (LLMs) exhibit emerging geospatial capabilities, stemming from their pre-training on vast unlabelled text datasets that are often derived from the Common Crawl corpus. However, the geospatial content within CC remains largely unexplored, impacting our understanding of LLMs' spatial reasoning. This paper investigates the prevalence of geospatial data in recent Common Crawl releases using Gemini, a powerful language model. By analyzing a sample of documents and manually revising the results, we estimate that between 1 in 5 and 1 in 6 documents contain geospatial information such as coordinates and street addresses. Our findings provide quantitative insights into the nature and extent of geospatial data within Common Crawl, and web crawl data in general. Furthermore, we formulate questions to guide future investigations into the geospatial content of available web crawl datasets and its influence on LLMs.

CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl

The Common Crawl (CC) corpus is the largest open web crawl dataset containing 9.5+ petabytes of data captured since 2008. The dataset is instrumental in training large language models, and as such it has been studied for (un)desirable content, and distilled for smaller, domain-specific datasets. However, to our knowledge, no research has been dedicated to using CC as a source of annotated geospatial data. In this paper, we introduce an efficient pipeline to extract annotated user-generated tracks from GPX files found in CC, and the resulting multimodal dataset with 1,416 pairings of human-written descriptions and MultiLineString vector data. The dataset can be used to study people's outdoor activity patterns, the way people talk about their outdoor experiences, and for developing trajectory generation or track annotation models.

Do Sentence Transformers Learn Quasi-Geospatial Concepts from General Text?

Sentence transformers are language models designed to perform semantic search. This study investigates the capacity of sentence transformers, fine-tuned on general question-answering datasets for asymmetric semantic search, to associate descriptions of human-generated routes across Great Britain with queries often used to describe hiking experiences. We find that sentence transformers have some zero-shot capabilities to understand quasi-geospatial concepts, such as route types and difficulty, suggesting their potential utility for routing recommendation systems.

Spatiotemporal Graph Neural Networks with Uncertainty Quantification for Traffic Incident Risk Prediction

Predicting traffic incident risks at granular spatiotemporal levels is challenging. The datasets predominantly feature zero values, indicating no incidents, with sporadic high-risk values for severe incidents. Notably, a majority of current models, especially deep learning methods, focus solely on estimating risk values, overlooking the uncertainties arising from the inherently unpredictable nature of incidents. To tackle this challenge, we introduce the Spatiotemporal Zero-Inflated Tweedie Graph Neural Networks (STZITD-GNNs). Our model merges the reliability of traditional statistical models with the flexibility of graph neural networks, aiming to precisely quantify uncertainties associated with road-level traffic incident risks. This model strategically employs a compound model from the Tweedie family, as a Poisson distribution to model risk frequency and a Gamma distribution to account for incident severity. Furthermore, a zero-inflated component helps to identify the non-incident risk scenarios. As a result, the STZITD-GNNs effectively capture the dataset's skewed distribution, placing emphasis on infrequent but impactful severe incidents. Empirical tests using real-world traffic data from London, UK, demonstrate that our model excels beyond current benchmarks. The forte of STZITD-GNN resides not only in its accuracy but also in its adeptness at curtailing uncertainties, delivering robust predictions over short (7 days) and extended (14 days) timeframes.

Re-designing cities with conditional adversarial networks

This paper introduces a conditional generative adversarial network to redesign a street-level image of urban scenes by generating 1) an urban intervention policy, 2) an attention map that localises where intervention is needed, 3) a high-resolution street-level image (1024 X 1024 or 1536 X1536) after implementing the intervention. We also introduce a new dataset that comprises aligned street-level images of before and after urban interventions from real-life scenarios that make this research possible. The introduced method has been trained on different ranges of urban interventions applied to realistic images. The trained model shows strong performance in re-modelling cities, outperforming existing methods that apply image-to-image translation in other domains that is computed in a single GPU. This research opens the door for machine intelligence to play a role in re-thinking and re-designing the different attributes of cities based on adversarial learning, going beyond the mainstream of facial landmarks manipulation or image synthesis from semantic segmentation.

CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning

Cycling is a promising sustainable mode for commuting and leisure in cities, however, the fear of getting hit or fall reduces its wide expansion as a commuting mode. In this paper, we introduce a novel method called CyclingNet for detecting cycling near misses from video streams generated by a mounted frontal camera on a bike regardless of the camera position, the conditions of the built, the visual conditions and without any restrictions on the riding behaviour. CyclingNet is a deep computer vision model based on convolutional structure embedded with self-attention bidirectional long-short term memory (LSTM) blocks that aim to understand near misses from both sequential images of scenes and their optical flows. The model is trained on scenes of both safe rides and near misses. After 42 hours of training on a single GPU, the model shows high accuracy on the training, testing and validation sets. The model is intended to be used for generating information that can draw significant conclusions regarding cycling behaviour in cities and elsewhere, which could help planners and policy-makers to better understand the requirement of safety measures when designing infrastructure or drawing policies. As for future work, the model can be pipelined with other state-of-the-art classifiers and object detectors simultaneously to understand the causality of near misses based on factors related to interactions of road-users, the built and the natural environments.

WeatherNet: Recognising weather and visual conditions from street-level images using deep residual learning

Extracting information related to weather and visual conditions at a given time and space is indispensable for scene awareness, which strongly impacts our behaviours, from simply walking in a city to riding a bike, driving a car, or autonomous drive-assistance. Despite the significance of this subject, it is still not been fully addressed by the machine intelligence relying on deep learning and computer vision to detect the multi-labels of weather and visual conditions with a unified method that can be easily used for practice. What has been achieved to-date is rather sectorial models that address limited number of labels that do not cover the wide spectrum of weather and visual conditions. Nonetheless, weather and visual conditions are often addressed individually. In this paper, we introduce a novel framework to automatically extract this information from street-level images relying on deep learning and computer vision using a unified method without any pre-defined constraints in the processed images. A pipeline of four deep Convolutional Neural Network (CNN) models, so-called the WeatherNet, is trained, relying on residual learning using ResNet50 architecture, to extract various weather and visual conditions such as Dawn/dusk, day and night for time detection, and glare for lighting conditions, and clear, rainy, snowy, and foggy for weather conditions. The WeatherNet shows strong performance in extracting this information from user-defined images or video streams that can be used not limited to: autonomous vehicles and drive-assistance systems, tracking behaviours, safety-related research, or even for better understanding cities through images for policy-makers.