Searcharxiv⌕ Search

arXiv subjects

Samir Ahmed

Publications and source records attributed to Samir Ahmed.

2 recordsLinked to original sources

Benchmarking Deep Learning Models for Wheelchair Configuration Classification in Accessible Automated Vehicle Applications

Making automated vehicles accessible requires consideration of vulnerable road users, including wheelchair users. To offer a more tailored experience that supports independence for this group, vehicle design needs to accommodate the wide range of wheelchair configurations. However, wheelchairs are individualized, varying in frame geometry, propulsion, and visual appearance. Moreover, occupants or accessories may obscure visual cues. Existing mobility-aid datasets only label the presence of a wheelchair, rather than describing its specific configuration. To fill this gap, this paper introduces the Wheelchair Configuration Image Dataset (WCID), comprising 467 face-blurred images across 192 capture groups solely for evaluation. Each image is annotated with (i) a two-class label of manual or powered, (ii) a chair subtype, (iii) occupancy, viewpoint, setting, lighting, occlusion, propulsion, and control, with a 273-image validation split and 194-image test split. Three convolutional neural network backbones and a frozen vision-language probe are trained on an external image dataset and evaluated on WCID to measure cross-dataset generalization, while also testing robustness using Gaussian blur. Convolutional models do well on clean images, but performance drops under strong blur, leaving a gap before deployment. Code, split assignments, labels, trained weights, and the face-blurred images is available at: https://github.com/Mi3-Lab/MAID

cs.CV↗

ViLDAR - Visible Light Sensing Based Speed Estimation using Vehicle's Headlamps

The introduction of light emitting diodes (LED) in automotive exterior lighting systems provides opportunities to develop viable alternatives to conventional communication and sensing technologies. Most of the advanced driver-assist and autonomous vehicle technologies are based on Radio Detection and Ranging (RADAR) or Light Detection and Ranging (LiDAR) systems that use radio frequency or laser signals, respectively. While reliable and real-time information on vehicle speeds is critical for traffic operations management and autonomous vehicles safety, RADAR or LiDAR systems have some deficiencies especially in curved road scenarios where the incidence angle is rapidly varying. In this paper, we propose a novel speed estimation system so-called the Visible Light Detection and Ranging (ViLDAR) that builds upon sensing visible light variation of the vehicle's headlamp. We determine the accuracy of the proposed speed estimator in straight and curved road scenarios. We further present how the algorithm design parameters and the channel noise level affect the speed estimation accuracy. For wide incidence angles, the simulation results show that the ViLDAR outperforms RADAR/LiDAR systems in both straight and curved road scenarios. A provisional patent (US#62/541,913) has been obtained for this work.

eess.SP↗