Search for: All records

The performance of object detection models in adverse weather conditions remains a critical challenge for intelligent transportation systems. Since advancements in autonomous driving rely heavily on extensive datasets, which help autonomous driving systems be reliable in complex driving environments, this study provides a comprehensive dataset under diverse weather scenarios like rain, haze, nighttime, or sun flares and systematically evaluates the robustness of state-of-the-art deep learning-based object detection frameworks. Our Adverse Driving Conditions Dataset features eight single weather effects and four challenging mixed weather effects, with a curated collection of 50,000 traffic images for each weather effect. State-of-the-art object detection models are evaluated using standard metrics, including precision, recall, and IoU. Our findings reveal significant performance degradation under adverse conditions compared to clear weather, highlighting common issues such as misclassification and false positives. For example, scenarios like haze combined with rain cause frequent detection failures, highlighting the limitations of current algorithms. Through comprehensive performance analysis, we provide critical insights into model vulnerabilities and propose directions for developing weather-resilient object detection systems. This work contributes to advancing robust computer vision technologies for safer and more reliable transportation in unpredictable real-world environments. 

Abstract The Farm to Fork (F2F) Strategy under the Green Deal aims to halve nutrient losses by 2030 in the European Union (EU). Here, using the nitrogen surplus as an indicator for nitrogen losses in agricultural areas, we explore a range of scenarios for nitrogen surplus reduction across EU landscapes. We identify four nitrogen surplus typologies, each responding differently to input reduction. A 20% decrease in synthetic fertilizer alone is projected to reduce the nitrogen surplus by only 10–16%, falling short of F2F goals. Specific top-down scenarios such as reducing synthetic fertilizer by 43% and animal manure by 4%, coupled with improved technological and management practices, can achieve a reduction of up to 30–45% in nitrogen surplus. Among the most ambitious scenarios, only a handful of EU countries (four to five) may meet the intended F2F nitrogen pollution targets. Achieving F2F goals requires region-specific strategies to reduce nitrogen use while improving efficiency and sustaining productivity.