Image segmentation is considered as a key research topic in the area of computer vision. It is pivotal in a broad range of real-life applications. Recently, the emergence of deep learning drives significant advancement in image segmentation; the developed systems are now capable of recognizing, segmenting, and classifying objects of specific interest in images. Generally, most of these techniques primarily focused on the asymmetric field of view or frontal view objects. This work explores widely used deep learning-based models for person segmentation using top view data set. The first model employed in this work is Fully Convolutional Neural Network (FCN) with Resnet-101 architecture. The network consists of a set of max-pooling and convolution layers to identify pixel-wise class labels and prediction of the mask. The second model is based on FCN called U-Net with Encoder-Decoder architecture. The encoder is mainly comprised of a contracting path, also called an encoder, which captures the context in the image and symmetric expanding path called decoder to enable accurate location. The third model used for top view person segmentation is a DeepLabV3 model also with encoder-decoder architecture. The encoder consists of trained Convolutional Neural Network (CNN) to encode feature maps of the input image. The decoder is used for up-sampling and reconstruction of output using important information extracted by the encoder. All segmentation models are firstly tested using pre-trained models (trained on frontal view data set). To improve the performance, these models are further trained using person data set captured from a top view. The output of all models consists of a segmented person in the top view images. The experimental results reveal the effectiveness and performance of segmentation models by achieving IoU of 83%, 84%, and 86% and mIoU of 80% 82%and 84% for FCN, U-Net, and DeepLabv3 respectively. Furthermore, the discussion is provided for output results with possible future guidelines.

Machine-health-surveillance systems are gaining popularity in industrial manufacturing systems due to the widespread availability of low-cost devices, sensors, and internet connectivity. In this regard, artificial intelligence provides valuable assistance in the form of deep learning methods to analyze and process big machine data. In diverse industrial applications, gears are considered a condemning element; many contributing failures occur due to an unexpected breakdown of the gears. In recent research, anomaly-detection and fault-diagnosis systems have been the gears’ most contributing content. Thus, in work, we presented a smart deep learning-based system to detect anomalies in an industrial machine. Our system used vibrational analysis methods as a deciding tool for different machinery-maintenance decisions. We will first perform a data analysis of the gearbox data set to analyze the data’s insights. By calculating and examining the machine’s vibration, we aim to determine the nature and severity of the defect in the machine and hence detect the anomaly. A gearbox’s vibration signal holds the fault’s signature in the gears, and earlier fault detection of the gearbox is achievable by examining the vibration signal using a deep learning technique. Therefore, we aim to propose a 6-layer autoencoder-based deep learning framework for anomaly detection and fault analysis using a publically available data set of wind-turbine components. The gearbox fault-diagnosis data set is utilized for experimentation, including collecting vibration attributes recorded using SpectraQuest’s gearbox fault-diagnostics simulator. Through comprehensive experiments, we have seen that the framework gains good results compared to others, with an overall accuracy of 91%.