The raindrops on the glass will affect driving safety, such as rear-view camera, outside mirror and windshield, etc. This article proposed a robust raindrop detection using deep learning on embedded platform with AI accelerator for real-time implementation. A training model is established through a convolution neural network (CNN)-like architecture to classify the images by the vehicle camera into three classes: no rain, heavy rain, and light rain. The classification results are used to control the speed of the motor to implement an automatic wiper control system. The training model, ResNet, is used to classify the image with good tradeoff between the computational cost and accuracy. For real-time application, the camera module on the Google Coral Dev board on embedded system platform is used to test the video stream and to estimate the performance of this system. Results show that the recognition accuracy reaches 95%, and the processing speed can achieve 20 frames per second (fps) on the embedded system.

The same class of objects clustering process in a frame is known as semantic segmentation. The deep convolutional neural network-based semantic segmentation needs large-scale computations and annotations for data training to reach real-time inference speeds. The heterogeneous image segmentation is a more challenging task to categorize each pixel of an image. However, the heterogeneous image semantic segmentation method extracts the features of visible and thermal images separately. We designed an efficient architecture with the multi-hybrid-autoencoder and decoder for Faster Heterogeneous Image (FHI) Semantic Segmentation. The proposed corresponding architecture has fewer layers resulting in lower parameters, higher inference speed, and Intersection over Union (IoU). The specialty of this architecture is the discrete autonomous feature extraction framework for RGB image and Thermal (T) image inputs with individual convolutional layers. Later, we combined the 4-channels (RGBT) convolution features to reduce computational complexity and robust the model performances. The proposed FHI-Unet semantic segmentation model experimented on NVIDIA Xavier NX edge AI platforms with standard accuracy under the real-time inference requirement. The proposed FHI-Unet model has the highest mIoU of 43.67 and the fastest real-time inference of 83.39 frames per second on edge AI implementation. The proposed approach improves 31.36% inference speed, 7.16% mAcc, and 5.1% mIoU on the Multi-spectral Semantic Segmentation Dataset compared with the existing works.

This paper presents a channel-wise average pooling and one dimension pixel-shuffle architecture for a denoising autoencoder (CPDAE) design that can be applied to efficiently remove electrode motion (EM) artifacts in an electrocardiogram (ECG) signal. The three advantages of the proposed design are as follows: (1) In the skip connection layer, less memory is needed to transfer the features extracted by the neural network; (2) Pixel shuffle and pixel unshuffle techniques with point-wise convolution are used to effectively reserve the key features generated from each layer in both the encoder and decoder; (3) Overall, fewer parameters are required to reconstruct the ECG signal. This paper describes three deep neural network models, namely CPDAE_Lite, CPDAE_Regular, and CPDAE_Full, which support various computational capacity and hardware arrangements. The three proposed structures involve an encoder and decoder with six, seven, and eight layers, respectively. Furthermore, the CPDAE_Lite, CPDAE_Regular, and CPDAE_Full structures require fewer multiply-accumulate operations—355.01, 56.96, and 14.69 million, respectively—and less parameter usage—2.69 million, 149.7 thousand, and 55.5 thousand, respectively. To evaluate the denoising performance, the MIT–BIH noise stress test database containing six signal-to-noise ratios (SNRs) of noisy ECGs was employed. The results demonstrated that the proposed models had a higher improvement of SNR and lower percentage root-mean-square difference than other state-of-the-art methods under various conditions of SNR.

The modeling of human body kye-points is the most significant aspect of pose estimation appropriately. Computer vision algorithm identifies human pose, body-movement, and action in many ways. Most of the previous works taken advantage for finding accuracy or efficiency in terms of speed. However, many techniques suffer for intensive computational demands with low-latency or higher proceeding speed. We have designed a unique approach for single-person pose estimation and action recognition which is well suited for fitness application and mobility activities. The proposed framework has been developed with a base network that provides an initial pose to further refinement through Intensive Feature Consistency (IFC) network. The IFC network enforces high-level constraints on the global body intensity correction and local body part adjustments. The proposed module reduces the impact of body joint movement diversity by interpreting long-term consistent view. We have illustrated the effectiveness of proposed framework through pose estimation accuracy improvement with two benchmark datasets. Which is specified state-of the- art performance of IFC network under the required real-time processing speed on the CPU platform. The IFC network has improved 99.1% of PCK body and 94.7% of PCK torso accuracy under 31 FPS, which is comparatively higher than the existing work.

Water is the important resource for human, however water leakage problem is very serious anywhere. To overcome this problem, this paper aims to design an automatic system for real-time water-flow monitoring and water resource management. The framework planned could be divided into two parts: client end for smart meters and the control center. The client end primarily integrates many water-meter readings in a local region and transmits the meter data back to the control center through wireless system. The control center transmits the request for meter reading, receiving, storing, and then processing data. The system framework is implemented with the co-design of hardware and software to achieve the desired results. With software management, this system can automatically read the water-meter degree during a period of time to charge the cost of water. Results show that the accuracy of water-flow can achieve over 97% after software correction. With real-time monitor for water leakage, this system can greatly improve the efficiency of water management for smart cities.

Current surveillance systems frequently use fixed-angle cameras and record a feed from those cameras. There are several disadvantages to such systems, including a low resolution for far away objects, a limited frame range and wasted disk space. This paper presents a novel algorithm for automatically detecting, tracking and zooming in on active targets. The object tracking system is connected to a camera that has a 360° horizontal and 90° vertical movement range. The combination of tracking, movement identification and zoom means that the system is able to effectively improve the resolution of small or distant objects. The object detection system allows for the disk space to be conserved as the system ceases recording when no valid targets are detected. Using an adaptive object segmentation algorithm, it is possible to detect the shape of moving objects efficiently. When processing multiple targets, each target is assigned a color and is treated separately. The tracking algorithm is able to adapt to targets moving at different speeds and is able to control the camera according to a predictive formula to prevent the loss of image quality due to camera trail. In the test environment, the zoom can sufficiently lock onto the head of a moving human; however, simultaneous tracking and zooming occasionally results in a failure to track. If this system is deployed with a facial recognition algorithm, the recognition accuracy can be effectively improved.