Recently, camera sensors have been widely used in a variety of applications, including advanced driver assistance systems (ADASs), surveillance systems, and unmanned aerial vehicles (UAVs). These sensors are often integrated with intelligent algorithms to automatically analyze information and perform specific functions. However, during rainy weather, droplets on the camera lens surface can obstruct the view, leading to degraded image quality and reduced algorithm performance. This paper quantitatively evaluates the effect of droplet contamination on image quality and object detection performance. Image quality degradation was analyzed using the modulation transfer function (MTF), with droplet volume and number as variables. Results show that the MTF50 decreased by up to 80% when the droplet volume reached 10 μL. To assess the effect on object detection, performance changes were evaluated across different detection algorithms. The findings reveal that droplet contamination can reduce the detection performance of small objects by up to 90%, as measured by the mean average precision (mAP) metric. Furthermore, degradation was more severe on hydrophilic surfaces compared to hydrophobic ones. This study demonstrates that droplet characteristics such as volume, number, and shape significantly influence both image quality and object detection performance. It provides critical insights into selecting appropriate camera lens materials by comparing hydrophilic and hydrophobic surfaces while also highlighting the susceptibility of intelligent algorithms to environmental factors and underscoring the importance of effective cleaning techniques.
This paper presents a practical contamination detection system for camera lenses using image analysis with deep learning. The proposed system can detect contamination in camera digital images through contamination learning utilizing deep learning, and it aims to prevent performance degradation of intelligent vision systems due to lens contamination in cameras. This system is based on the object detection algorithm YOLO (v5n, v5s, v5m, v5l, and v5x), which is trained with 4000 images captured under different lighting and background conditions. The trained models showed that the average precision improves as the algorithm size increases, especially for YOLOv5x, which showed excellent efficiency in detecting droplet contamination within 23 ms. They also achieved an average precision (mAP@0.5) of 87.46%, recall (mAP@0.5:0.95) of 51.90%, precision of 90.28%, recall of 81.47%, and F1 score of 85.64%. As a proof of concept, we demonstrated the identification and removal of contamination on camera lenses by integrating a contamination detection system and a transparent heater-based cleaning system. The proposed system is anticipated to be applied to autonomous driving systems, public safety surveillance cameras, environmental monitoring drones, etc., to increase operational safety and reliability.
This paper presents a miniature robot designed for monitoring its surroundings and exploring small and complex environments by skating on the surface of water. The robot is mainly made of extruded polystyrene insulation (XPS) and Teflon tubes and is propelled by acoustic bubble-induced microstreaming flows generated by gaseous bubbles trapped in the Teflon tubes. The robot’s linear motion, velocity, and rotational motion are tested and measured at different frequencies and voltages. The results show that the propulsion velocity is proportional to the applied voltage but highly depends on the applied frequency. The maximum velocity occurs between the resonant frequencies for two bubbles trapped in Teflon tubes of different lengths. The robot’s maneuvering capability is demonstrated by selective bubble excitation based on the concept of different resonant frequencies for bubbles of different volumes. The proposed water skating robot can perform linear propulsion, rotation, and 2D navigation on the water surface, making it suitable for exploring small and complex water environments.
Digital microfluidics (DMF) platforms are automated sample-processing platforms that can electrically manipulate nanoliter-to-microliter-scale droplets to perform various droplet operations, such as transport, merging, splitting, and mixing. However, conventional DMF platforms mainly rely on GUI-based operation, requiring physical input devices. In this study, we propose a voice-command-based DMF platform that converts the user’s voice commands into electrode activation sequences for droplet manipulation through three components: a speech recognition module, a control signal conversion module, and a droplet actuation unit. The platform successfully executed voice commands for directional movement, target-position transport, merging, splitting, and repeated movement. The results confirmed that diverse voice commands could be converted into corresponding electrode activation sequences and executed as physical droplet manipulation. Quantitative evaluation showed a command-processing latency of 0.3–0.5 s and an average command execution accuracy of 93%. These values were obtained from a single English-speaking experimenter using predefined commands under uncharacterized laboratory noise conditions. Furthermore, a mixing operation composed of transport, merging, and repeated movement demonstrated the extensibility of the proposed framework to complex multistep droplet protocols. These results suggest that voice commands can serve as an intuitive hands-free interface for DMF platforms while reducing dependence on physical input devices.