RESUMEN
Recent advancements in computer vision technology, developments in sensors and sensor-collecting approaches, and the use of deep and transfer learning approaches have excelled in the development of autonomous vehicles. On-road vehicle detection has become a task of significant importance, especially due to exponentially increasing research on autonomous vehicles during the past few years. With high-end computing resources, a large number of deep learning models have been trained and tested for on-road vehicle detection recently. Vehicle detection may become a challenging process especially due to varying light and weather conditions like night, snow, sand, rain, foggy conditions, etc. In addition, vehicle detection should be fast enough to work in real time. This study investigates the use of the recent YOLO version, YOLOx, to detect vehicles in bad weather conditions including rain, fog, snow, and sandstorms. The model is tested on the publicly available benchmark dataset DAWN containing images containing four bad weather conditions, different illuminations, background, and number of vehicles in a frame. The efficacy of the model is evaluated in terms of precision, recall, and mAP. The results exhibit the better performance of YOLOx-s over YOLOx-m and YOLOx-l variants. YOLOx-s has 0.8983 and 0.8656 mAP for snow and sandstorms, respectively, while its mAP for rain and fog is 0.9509 and 0.9524, respectively. The performance of models is better for snow and foggy weather than rainy weather sandstorms. Further experiments indicate that enhancing image quality using multiscale retinex improves YOLOx performance.
RESUMEN
Microfluidic devices have immense potential for widespread community use, but a current bottleneck is the transition from research prototyping into mass production because the gold standard prototyping strategy is too costly and labor intensive when scaling up fabrication throughput. For increased throughput, it is common to mold devices out of thermoplastics due to low per-unit costs at high volumes. However, conventional fabrication methods have high upfront development expenses with slow mold fabrication methods that limit the speed of design evolution for expedited marketability. To overcome this limitation, we propose a rapid prototyping protocol to fabricate thermoplastic devices from a stereolithography (SLA) 3D printed template through intermediate steps akin to those employed in soft lithography. We apply this process towards the design of self-operating capillaric circuits, well suited for deployment as low-cost decentralized assays. Rapid development of these geometry- and material-dependent devices benefits from prototyping with thermoplastics. We validated the constructed capillaric circuits by performing an autonomous, pre-programmed, bead-based immunofluorescent assay for protein quantification. Overall, this prototyping method provides a valuable means for quickly iterating and refining microfluidic devices, paving the way for future scaling of production.