Ethiopian Banknote Recognition Using Convolutional Neural Network and Its Prototype Development Using Embedded Platform

Money transactions can be performed by automated self-service machines like ATMs for money deposits and withdrawals, banknote counters and coin counters, automatic vending machines, and automatic smart card charging machines. There are four important functions such as banknote recognition, counterfeit banknote detection, serial number recognition, and fitness classification which are furnished with these devices. Therefore, we need a robust system that can recognize banknotes and classify them into denominations that can be used in these automated machines. However, the most widely available banknote detectors are hardware systems that use optical and magnetic sensors to detect and validate banknotes. These banknote detectors are usually designed for specific country banknotes. Reprogramming such a system to detect banknotes is very difficult. In addition, researchers have developed banknote recognition systems using deep learning artificial intelligence technology like CNN and R-CNN. However, in these systems, dataset used for training is relatively small, and the accuracy of banknote recognition is found smaller. The existing systems also do not include implementation and its development using embedded systems. In this research work, we collected various Ethiopian currencies with different ages and conditions and applied various optimization techniques for CNN architects to identify the fake notes. Experimental analysis has been demonstrated with different models of CNN such as InceptionV3, MobileNetV2, XceptionNet, and ResNet50. MobileNetV2 with RMSProp optimization technique with batch size 32 is found to be a robust and reliable Ethiopian banknote detector and achieved superior accuracy of 96.4% in comparison to other CNN models. Selected model MobileNetV2 with RMSProp optimization has been implemented through an embedded platform by utilizing Raspberry Pi 3 B+ and other peripherals. Further, real-time identification of fake notes in a Web-based user interface (UI) has also been proposed in the research.

Optimization of an unscented Kalman filter for an embedded platform

The unscented Kalman filter (UKF) is finding increased application in biological fields. While realizing a complex UKF system in a low-power embedded platform offers many potential benefits including wearability, it also poses significant design challenges. Here we present a method for optimizing a UKF system for realization in an embedded platform. The method seeks to minimize both computation time and error in UKF state reconstruction and forecasting. As a case study, we applied the method to a model for the rat sleep-wake regulatory system in which 432 variants of the UKF over six different variables are considered. The optimization method is divided into three stages that assess computation time, state forecast error, and state reconstruction error. We apply a cost function to variants that pass all three stages to identify a variant that computes 27 times faster than the reference variant and maintains required levels of state estimation and forecasting accuracy. We draw the following insights: 1) process noise provides leeway for simplifying the model and its integration in ways that speed computation time while maintaining state forecasting accuracy, 2) the assimilation of observed data during the UKF correction step provides leeway for simplifying the UKF structure in ways that speed computation time while maintaining state reconstruction accuracy, and 3) the optimization process can be accelerated by decoupling variables that directly impact the underlying model from variables that impact the UKF structure.

DNA-Based Cryptographic Method for the Internet of Things

Internet of Things (IoT) is a set of connected smart devices providing and sharing rich data in real-time without involving a human being. However, IoT is a security nightmare because like in the early computer systems, security issues are not considered in the design step. Thereby, each IoT system could be susceptible to malicious users and uses. To avoid these types of situations, many approaches and techniques are proposed by both academic and industrial researches.DNA computing is an emerging and relatively new field dealing with data encryption using a DNA computing concepts. This technique allows rapid and secure data transfer between connected objects with low power consumption. In this paper, authors propose a symmetric cryptography method based on DNA. This method consists in cutting the message to encrypt/decrypt in blocks of characters and use a symmetric key extracted from a chromosome for encryption and decryption. Implemented on the embedded platform of a Raspberry Pi, the proposed method shows good performances in terms of robustness, complexity and attack resistance.

Implementation of the PointPillars Network for 3D Object Detection in Reprogrammable Heterogeneous Devices Using FINN

In this paper, we present a hardware-software implementation of a deep neural network for object detection based on a point cloud obtained by a LiDAR sensor. The PointPillars network was used in the research, as it is a reasonable compromise between detection accuracy and calculation complexity. The Brevitas / PyTorch tools were used for network quantisation (described in our previous paper) and the FINN tool for hardware implementation in the reprogrammable Zynq UltraScale+ MPSoC device. The obtained results show that quite a significant computation precision limitation along with a few network architecture simplifications allows the solution to be implemented on a heterogeneous embedded platform with maximum 19% AP loss in 3D, maximum 8% AP loss in BEV and execution time 375ms (the FPGA part takes 262ms). We have also compared our solution in terms of inference speed with a Vitis AI implementation proposed by Xilinx (19 Hz frame rate). Especially, we have thoroughly investigated the fundamental causes of differences in the frame rate of both solutions. The code is available at https://github.com/vision-agh/pp-finn.

Real-Time LiDAR Point Cloud Semantic Segmentation for Autonomous Driving

LiDAR has been widely used in autonomous driving systems to provide high-precision 3D geometric information about the vehicle’s surroundings for perception, localization, and path planning. LiDAR-based point cloud semantic segmentation is an important task with a critical real-time requirement. However, most of the existing convolutional neural network (CNN) models for 3D point cloud semantic segmentation are very complex and can hardly be processed at real-time on an embedded platform. In this study, a lightweight CNN structure was proposed for projection-based LiDAR point cloud semantic segmentation with only 1.9 M parameters that gave an 87% reduction comparing to the state-of-the-art networks. When evaluated on a GPU, the processing time was 38.5 ms per frame, and it achieved a 47.9% mIoU score on Semantic-KITTI dataset. In addition, the proposed CNN is targeted on an FPGA using an NVDLA architecture, which results in a 2.74x speedup over the GPU implementation with a 46 times improvement in terms of power efficiency.

Research on Lightweight Infrared Pedestrian Detection Model Algorithm for Embedded Platform

Due to the limitation of energy consumption and power consumption, the embedded platform cannot meet the real-time requirements of the far-infrared image pedestrian detection algorithm. To solve this problem, this paper proposes a new real-time infrared pedestrian detection algorithm (RepVGG-YOLOv4, Rep-YOLO), which uses RepVGG to reconstruct the YOLOv4 backbone network, reduces the amount of model parameters and calculations, and improves the speed of target detection; using space spatial pyramid pooling (SPP) obtains different receptive field information to improve the accuracy of model detection; using the channel pruning compression method reduces redundant parameters, model size, and computational complexity. The experimental results show that compared with the YOLOv4 target detection algorithm, the Rep-YOLO algorithm reduces the model volume by 90%, the floating-point calculation is reduced by 93.4%, the reasoning speed is increased by 4 times, and the model detection accuracy after compression reaches 93.25%.

Lightweight target detection model for embedded platform

The detection speed of target detection algorithm depends on the performance of computer equipment. Aiming at the problems of slow detection speed and difficult trade-off between detection accuracy and detection speed when the target detection model is used in embedded devices, a lightweight target detection model based on the improved Tiny YOLO-V3 is proposed. Firstly, we analyze the time consumption of each layer structure in the convolutional neural network, and do a lot of experiments and tests. Then, we compress the time-consuming structure substantially. Secondly, we propose the segmentation and fusion module to improve the detection accuracy. Finally, we use the remote sensing data set of Wuhan University for experiments, and the experimental results show that compared with Tiny YOLO-V3, the detection speed is improved by 4 times, and the accuracy is improved by 2 percentage points.