Real-time pedestrian detection is an important task for unmanned driving systems and video surveillance.The existing pedestrian detection methods often work at low speed and also fail to detect smaller and densely dis...Real-time pedestrian detection is an important task for unmanned driving systems and video surveillance.The existing pedestrian detection methods often work at low speed and also fail to detect smaller and densely distributed pedestrians by losing some of their detection accuracy in such cases.Therefore,the proposed algorithm YOLOv2(“YOU ONLY LOOK ONCE Version 2”)-based pedestrian detection(referred to as YOLOv2PD)would be more suitable for detecting smaller and densely distributed pedestrians in real-time complex road scenes.The proposed YOLOv2PD algorithm adopts a Multi-layer Feature Fusion(MLFF)strategy,which helps to improve the model’s feature extraction ability.In addition,one repeated convolution layer is removed from the final layer,which in turn reduces the computational complexity without losing any detection accuracy.The proposed algorithm applies the K-means clustering method on the Pascal Voc-2007+2012 pedestrian dataset before training to find the optimal anchor boxes.Both the proposed network structure and the loss function are improved to make the model more accurate and faster while detecting smaller pedestrians.Experimental results show that,at 544×544 image resolution,the proposed model achieves 80.7%average precision(AP),which is 2.1%higher than the YOLOv2 Model on the Pascal Voc-2007+2012 pedestrian dataset.Besides,based on the experimental results,the proposed model YOLOv2PD achieves a good trade-off balance between detection accuracy and real-time speed when evaluated on INRIA and Caltech test pedestrian datasets and achieves state-of-the-art detection results.展开更多
Owing to the ppb-level detection standard toward the toxic and harmful gas,the detection of trace gases has become an important subject in the field of indoor environment management.However,the traditional resistive g...Owing to the ppb-level detection standard toward the toxic and harmful gas,the detection of trace gases has become an important subject in the field of indoor environment management.However,the traditional resistive gas sensors hardly meet the requirement due to the weak signal generated by trace gas molecules that are difficult to capture.Herein,a visible-light-assisted Pd/TiO_(2)gas sensor is proposed to endow the effective detection of trace formaldehyde(HCHO)gas without heating temperature.Benefiting from the enhanced photocatalytic properties of TiO_(2)by Pd decoration,the visible-light-assisted Pd/TiO_(2)gas sensor can detect the HCHO gas as low as80×10^(–9)at room temperature.The successful preparation of nanoscale TiO_(2)sensing layer is facilitated by the ultrathin carbon nanotube interdigital electrode in the gas sensor,which avoids the discontinuity of the sensing layer caused by the excessive thickness of the traditional metal electrode.In addition,the whole preparation process of the Pd/TiO_(2)gas sensor with carbon nanotube electrodes is compatible with mainstream CMOS fabrication technology,which is expected to realize the batch fabrication and micro-integrated application of gas sensors.It is expected that our work can provide a new strategy for the batch preparation of high-performance trace HCHO gas sensors and their future applications in portable electronic devices such as smartphones.展开更多
采用改进的Hummers法和硼氢化钠还原法制备Pd/石墨烯催化剂,并采用XRD、SEM、XPS、TEM等技术对其进行表征.将该催化剂修饰于玻碳电极表面,制备出Pd/石墨烯/玻碳电极,使用循环伏安法研究了检测4-氯酚的最佳工作条件.研究结果表明,所得石...采用改进的Hummers法和硼氢化钠还原法制备Pd/石墨烯催化剂,并采用XRD、SEM、XPS、TEM等技术对其进行表征.将该催化剂修饰于玻碳电极表面,制备出Pd/石墨烯/玻碳电极,使用循环伏安法研究了检测4-氯酚的最佳工作条件.研究结果表明,所得石墨烯表面平整光滑,以零价态存在的Pd纳米颗粒均匀分散到石墨烯上,平均粒径为（6.5±0.05）nm.检测4-氯酚的最佳支持电解质为0.1 mol·L-1、p H 6.8的磷酸-磷酸钠缓冲溶液（PBS）,峰电流与扫描速率的平方根呈良好的线性关系（R2=0.992）,该电极的线性范围为1~100μmol·L-1（R2=0.967）,检测限为0.57μmol·L-1（S/N=3）,且具有良好的重现性和稳定性.本文所研制的Pd/石墨烯/玻碳电极具有较高的催化活性,提供了一种简便快捷、重现性好的检测4-氯酚的方法.展开更多
Here,we report a Pd/PdO_(x) sensing material that achieves 1-s detection of 4% H_(2) gas(i.e.,the lower explosive limit concentration for H_(2))at room temperature in air.The Pd/PdO_(x) material is a network of interc...Here,we report a Pd/PdO_(x) sensing material that achieves 1-s detection of 4% H_(2) gas(i.e.,the lower explosive limit concentration for H_(2))at room temperature in air.The Pd/PdO_(x) material is a network of interconnected nanoscopic domains of Pd,PdO,and PdO_(2).Upon exposure to 4% H_(2),PdO and PdO_(2) in the Pd/PdO_(x) are immediately reduced to metallic Pd,generating over a>90% drop in electrical resistance.The mechanistic study reveals that the Pd/PdO_(2) interface in Pd/PdOx is responsible for the ultrafast PdO_(x) reduction.Metallic Pd at the Pd/PdO_(2) interface enables fast H_(2) dissociation to adsorbed H atoms,significantly lowering the PdO2 reduction barrier.In addition,control experiments suggest that the interconnectivity of Pd,PdO,and PdO2 in our Pd/PdO_(x) sensing material further facilitates the reduction of PdO,which would otherwise not occur.The 1-s response time of Pd/PdO_(x) under ambient conditions makes it an excellent alarm for the timely detection of hydrogen gas leaks.展开更多
基金The authors are grateful to the Deanship of Scientific Research,King Saud University,Riyadh,Saudi Arabia,for funding this work through the Vice Deanship of Scientific Research Chairs:Research Chair of Pervasive and Mobile Computing.
文摘Real-time pedestrian detection is an important task for unmanned driving systems and video surveillance.The existing pedestrian detection methods often work at low speed and also fail to detect smaller and densely distributed pedestrians by losing some of their detection accuracy in such cases.Therefore,the proposed algorithm YOLOv2(“YOU ONLY LOOK ONCE Version 2”)-based pedestrian detection(referred to as YOLOv2PD)would be more suitable for detecting smaller and densely distributed pedestrians in real-time complex road scenes.The proposed YOLOv2PD algorithm adopts a Multi-layer Feature Fusion(MLFF)strategy,which helps to improve the model’s feature extraction ability.In addition,one repeated convolution layer is removed from the final layer,which in turn reduces the computational complexity without losing any detection accuracy.The proposed algorithm applies the K-means clustering method on the Pascal Voc-2007+2012 pedestrian dataset before training to find the optimal anchor boxes.Both the proposed network structure and the loss function are improved to make the model more accurate and faster while detecting smaller pedestrians.Experimental results show that,at 544×544 image resolution,the proposed model achieves 80.7%average precision(AP),which is 2.1%higher than the YOLOv2 Model on the Pascal Voc-2007+2012 pedestrian dataset.Besides,based on the experimental results,the proposed model YOLOv2PD achieves a good trade-off balance between detection accuracy and real-time speed when evaluated on INRIA and Caltech test pedestrian datasets and achieves state-of-the-art detection results.
基金financially supported by the National Natural Science Foundation of China(Nos.62071410 and 62101477)Hunan Provincial Natural Science Foundation(No.2021JJ40542)the Postgraduate Scientific Research Innovation Project of Hunan Province(No.CX20210627)。
文摘Owing to the ppb-level detection standard toward the toxic and harmful gas,the detection of trace gases has become an important subject in the field of indoor environment management.However,the traditional resistive gas sensors hardly meet the requirement due to the weak signal generated by trace gas molecules that are difficult to capture.Herein,a visible-light-assisted Pd/TiO_(2)gas sensor is proposed to endow the effective detection of trace formaldehyde(HCHO)gas without heating temperature.Benefiting from the enhanced photocatalytic properties of TiO_(2)by Pd decoration,the visible-light-assisted Pd/TiO_(2)gas sensor can detect the HCHO gas as low as80×10^(–9)at room temperature.The successful preparation of nanoscale TiO_(2)sensing layer is facilitated by the ultrathin carbon nanotube interdigital electrode in the gas sensor,which avoids the discontinuity of the sensing layer caused by the excessive thickness of the traditional metal electrode.In addition,the whole preparation process of the Pd/TiO_(2)gas sensor with carbon nanotube electrodes is compatible with mainstream CMOS fabrication technology,which is expected to realize the batch fabrication and micro-integrated application of gas sensors.It is expected that our work can provide a new strategy for the batch preparation of high-performance trace HCHO gas sensors and their future applications in portable electronic devices such as smartphones.
文摘采用改进的Hummers法和硼氢化钠还原法制备Pd/石墨烯催化剂,并采用XRD、SEM、XPS、TEM等技术对其进行表征.将该催化剂修饰于玻碳电极表面,制备出Pd/石墨烯/玻碳电极,使用循环伏安法研究了检测4-氯酚的最佳工作条件.研究结果表明,所得石墨烯表面平整光滑,以零价态存在的Pd纳米颗粒均匀分散到石墨烯上,平均粒径为（6.5±0.05）nm.检测4-氯酚的最佳支持电解质为0.1 mol·L-1、p H 6.8的磷酸-磷酸钠缓冲溶液（PBS）,峰电流与扫描速率的平方根呈良好的线性关系（R2=0.992）,该电极的线性范围为1~100μmol·L-1（R2=0.967）,检测限为0.57μmol·L-1（S/N=3）,且具有良好的重现性和稳定性.本文所研制的Pd/石墨烯/玻碳电极具有较高的催化活性,提供了一种简便快捷、重现性好的检测4-氯酚的方法.
基金The work at Wayne State University and the Pacific Northwest National Laboratory was supported by the U.S.Department of Energy(DOE),Office of Science,Office of Basic Energy Sciences,through Award#78705In addition,L.L.and X.G.acknowledge support from National Science Foundation under award CHE-1943737.L.Z.and S.W.L.acknowledge support from the National Natural Science Foundation of China(No.22103047)Hefei National Laboratory for Physical Sciences at the Microscale(No.KF2020107).
文摘Here,we report a Pd/PdO_(x) sensing material that achieves 1-s detection of 4% H_(2) gas(i.e.,the lower explosive limit concentration for H_(2))at room temperature in air.The Pd/PdO_(x) material is a network of interconnected nanoscopic domains of Pd,PdO,and PdO_(2).Upon exposure to 4% H_(2),PdO and PdO_(2) in the Pd/PdO_(x) are immediately reduced to metallic Pd,generating over a>90% drop in electrical resistance.The mechanistic study reveals that the Pd/PdO_(2) interface in Pd/PdOx is responsible for the ultrafast PdO_(x) reduction.Metallic Pd at the Pd/PdO_(2) interface enables fast H_(2) dissociation to adsorbed H atoms,significantly lowering the PdO2 reduction barrier.In addition,control experiments suggest that the interconnectivity of Pd,PdO,and PdO2 in our Pd/PdO_(x) sensing material further facilitates the reduction of PdO,which would otherwise not occur.The 1-s response time of Pd/PdO_(x) under ambient conditions makes it an excellent alarm for the timely detection of hydrogen gas leaks.
