A pedestrian detection algorithm for low light and dense crowd Based on improved YOLO algorithm

The real-time pedestrian detection algorithm requires the model to be lightweight and robust. At the same time, the pedestrian object detection problem has the characteristics of aerial view Angle shooting, object overlap and weak light, etc. In order to design a more robust real-time detection model in weak light and crowded scene, this paper based on YOLO, raised a more efficient convolutional network. The experimental results show that, compared with YOLOX Network, the improved YOLO Network has a better detection effect in the lack of light scene and dense crowd scene, has a 5.0% advantage over YOLOX-s for pedestrians AP index, and has a 44.2% advantage over YOLOX-s for fps index.

Towards high performance near-infrared photo detectors based on SnS nanowires

Compared with bulk structures, semiconductor nanowires exhibit a higher surface-to-volume ratio, as well as unique electrical and optical properties. Due to its narrow band gap, tin (ii) sulfide (SnS) nano wire is a promising candidate for constructing near-infrared (NIR) photodetectors. Uniformly distributed and well aligned SnS nanowires were grown on mica substrate by chemical vapor deposition, and NIR photodetectors with Au (Au-device) and Al (Al-device) as the electrode were fabricated and characterized. Compared to Au-device, Al-device achieved higher photodetectivity due to reduced dark current. More importantly by incorporating photosensitive lead phthalocyanine (PbPc) film into Al-device, both responsivity and detectivity could be apparently improved, especially at weak light intensities. Under a weak light intensity of 0.79 mW/cm2 the photoresponsivity and specific detectivity were improved from ~0.56 A/W and 5.1×1010 Jones to 0.96 A/W and 8.4×1010 Jones, respectively.

REAL OBJECT DETECTION SYSTEM FOR IRAQ TRAFFIC SIGNS BASED ON MASK R-CNN

Traffic signs object detection has gained great interest in recent years, as one of the most important object detector applications. Traffic signs detection is based on deep learning, which gives it the benefit of high detection precision and timely response to condition changes of the traffic. Therefore, this paper shows an efficient method for detecting traffic signs in real-time. Hence, it implements a new Iraqi Traffic Sign Detection Benchmark (IQTSDB) dataset based on Mask Region-based Convolutional Neural Network (Mask R-CNN). The results show that the implementation of IQTSDB dataset with Mask R-CNN has a great efficiency in different conditions such as sunny, cloudy, weak light, and rainy conditions. In addition, the real video captured for traffic signs in Baghdad has been taken and compared to the German Traffic Signs Detection Benchmark (GTSDB) dataset. The IQTSDB dataset has a better performance than GTSDB dataset based on the performance parameters training loss and mean Average Precision (mAP).

An Adaptive Pose Fusion Method for Indoor Map Construction

The vision-based robot pose estimation and mapping system has the disadvantage of low pose estimation accuracy and poor local detail mapping effects, while the modeling environment has poor features, high dynamics, weak light, and multiple shadows, among others. To address these issues, we propose an adaptive pose fusion (APF) method to fuse the robot’s pose and use the optimized pose to construct an indoor map. Firstly, the proposed method calculates the robot’s pose by the camera and inertial measurement unit (IMU), respectively. Then, the pose fusion method is adaptively selected according to the motion state of the robot. When the robot is in a static state, the proposed method directly uses the extended Kalman filter (EKF) method to fuse camera and IMU data. When the robot is in a motive state, the weighted coefficient is determined according to the matching success rate of the feature points, and the weighted pose fusion (WPF) method is used to fuse camera and IMU data. According to the different states, a series of new poses of the robot are obtained. Secondly, the fusion optimized pose is used to correct the distance and azimuth angle of the laser points obtained by LiDAR, and a Gauss–Newton iterative matching process is used to match the corresponding laser points to construct an indoor map. Finally, a pose fusion experiment is designed, and the EuRoc data and the measured data are used to verify the effectiveness of this method. The experimental results confirm that this method provides higher pose estimation accuracy compared with the robust visual inertial odometry (ROVIO) and visual-inertial ORB-SLAM (VI ORB-SLAM) algorithms. Compared with the Cartographer algorithm, this method provides higher two-dimensional map modeling accuracy and modeling performance.

Transparent graphene electrodes based hybrid perovskites photodetectors with broad spectral response from UV-visible to near-infrared

A new class of transparent graphene electrode based organic-inorganic halide perovskite photodetectors with broad spectral response is developed. These ultrasensitive devices exhibit high ON/OFF current ratio, high LDR, broad spectral range, excellent detection for weak light and easy fabrication with low-cost. Their semi-transparent feature and distinct photodetecting function for both sides would provide new applications affecting our daily lives.

Method For Measuring Sub-Micron Facula At Single-Photon Level With Silicon Photomultiplier

Sub-micron faculae (light spots) at the single-photon level have important applications in many fields. This report demonstrates a method for measuring facula size at the sub-micron single-photon level indirectly. The developed method utilizes Silicon Photomultipliers (SiPMs) as the single-photon response detectors, combined with a nano-positioning stage. The approach involves one- or two-dimensional space scanning and a deconvolution operation, which enable evaluations of the size and spatial distribution of focused facula in a single-photon-level pulsed laser. The results indicate that the average full width at half maximum of the faculae is about 0.66 µm, which is close to the nominal resolution of the objective lens of the microscope (0.42 µm). The proposed method has two key advantages: (1) it can measure sub-micron facula at the single-photon level, and (2) the sub-micron facula can easily be aligned with the detector because the array area of the avalanche photodiode cells in SiPM is usually larger than one square millimeter, and there is no need to put an optical slit, knife edge, or pinhole in front of the detector. The method described herein is applicable in weak light facula detection related fields.