Advances in passive acoustic detection, localization, and tracking applied to unmanned underwater vehicles

Detection, classification, localization, and tracking (DCLT) of unmanned underwater vehicles (UUVs) in the presence of shipping traffic is a critical task for passive acoustic harbor security systems. In general, vessels can be tracked by their unique acoustic signature due to machinery vibration and cavitation noise. However, cavitation noise of UUVs is considerably quieter than ships and boats, making detection significantly more challenging. In this thesis, I demonstrated that it is possible to passively track a UUV from its highfrequency motor noise using a stationary array in shallow-water experiments with passing boats. First, causes of high frequency tones were determined through direct measurements of two UUVs at a range of speeds. From this analysis, common and dominant features of noise were established: strong tones at the motor’s pulse-width modulated frequency and its harmonics. From the unique acoustic signature of the motor, I derived a high-precision, remote sensing method for estimating propeller rotation rate. In shallow-water UUV field experiments, I demonstrated that detecting a UUV from motor noise, in comparison to broadband noise from the vehicle, reduces false alarms from 45% to 8.4% for 90% true detections. Beamforming on the motor noise, in comparison to broadband noise, improved the bearing accuracy by a factor of 3.2×. Because the signal is also high-frequency, the Doppler effect on motor noise is observable and I demonstrate that range rate can be measured. Furthermore, measuring motor noise was a superior method to the “detection of envelope modulation on noise” algorithm for estimating the propeller rotation rate. Extrapolating multiple measurements from the motor signature is significant because Bearing-Doppler-RPM measurements outperform traditional bearing-Doppler target motion analysis. In the unscented Kalman filter implementation, the tracking solution accuracy for bearing, bearing rate, range, and range rate improved by a factor 2.2×, 15.8×, 3.1×, and 6.2× respectively. These findings are significant for improving UUV localization and tracking, and for informing the next-generation of quiet UUV propulsion systems.

A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images

In this work we present a novel end-to-end solution for tracking objects (i.e., vessels), using video streams from aerial drones, in dynamic maritime environments. Our method relies on deep features, which are learned using realistic simulation data, for robust object detection, segmentation and tracking. Furthermore, we propose the use of rotated bounding-box representations, which are computed by taking advantage of pixel-level object segmentation, for improved tracking accuracy, by reducing erroneous data associations during tracking, when combined with the appearance-based features. A thorough set of experiments and results obtained in a realistic shipyard simulation environment, demonstrate that our method can accurately, and fast detect and track dynamic objects seen from a top-view.

Object Localization and Tracking System Using Multiple Ultrasonic Sensors with Newton–Raphson Optimization and Kalman Filtering Techniques

In this paper, an object localization and tracking system is implemented with an ultrasonic sensing technique and improved algorithms. The system is composed of one ultrasonic transmitter and five receivers, which uses the principle of ultrasonic ranging measurement to locate the target object. This system has several stages of locating and tracking the target object. First, a simple voice activity detection (VAD) algorithm is used to detect the ultrasonic echo signal of each receiving channel, and then a demodulation method with a low-pass filter is used to extract the signal envelope. The time-of-flight (TOF) estimation algorithm is then applied to the signal envelope for range measurement. Due to the variations of position, direction, material, size, and other factors of the detected object and the signal attenuation during the ultrasonic propagation process, the shape of the echo waveform is easily distorted, and TOF estimation is often inaccurate and unstable. In order to improve the accuracy and stability of TOF estimation, a new method of TOF estimation by fitting the general (GN) model and the double exponential (DE) model on the suitable envelope region using Newton–Raphson (NR) optimization with Levenberg–Marquardt (LM) modification (NRLM) is proposed. The final stage is the object localization and tracking. An extended Kalman filter (EKF) is designed, which inherently considers the interference and outlier problems of range measurement, and effectively reduces the interference to target localization under critical measurement conditions. The performance of the proposed system is evaluated by the experimental evaluation of conditions, such as stationary pen localization, stationary finger localization, and moving finger tracking. The experimental results verify the performance of the system and show that the system has a considerable degree of accuracy and stability for object localization and tracking.

ETDR: An Exploratory View of Text Detection and Recognition in Images and Videos

Images and videos with text content are a direct source of information. Today, there is a high need for image and video data that can be intelligently analyzed. A growing number of researchers are focusing on text identification, making it a hot issue in machine vision research. Since this opens the way, several real-time-based applications such as text detection, localization, and tracking have become more prevalent in text analysis systems. To find out more about how text information may be extracted, have a look at our survey. This study presents a trustworthy dataset for text identification in images and videos at first. The second part of the article details the numerous text formats, both in images and video. Third, the process flow for extracting information from the text and the existing machine learning and deep learning techniques used to train the model was described. Fourth, explain assessment measures that are used to validate the model. Finally, it integrates the uses and difficulties of text extraction across a wide range of fields. Difficulties focus on the most frequent challenges faced in the actual world, such as capturing techniques, lightning, and environmental conditions. Images and videos have evolved into valuable sources of data. The text inside the images and video provides a massive quantity of facts and statistics. However, such data is not easy to access. This exploratory view provides easier and more accurate mathematical modeling and evaluation techniques to retrieve the text in image and video into an accessible form.

Alternatives for Locating People Using Cameras and Embedded AI Accelerators: A Practical Approach

Indoor positioning systems usually rely on RF-based devices that should be carried by the targets, which is non-viable in certain use cases. Recent advances in AI have increased the reliability of person detection in images, thus, enabling the use of surveillance cameras to perform person localization and tracking. This paper evaluates the performance of indoor person location using cameras and edge devices with AI accelerators. We describe the video processing performed in each edge device, including the selected AI models and the post-processing of their outputs to obtain the positions of the detected persons and allow their tracking. The person location is based on pose estimation models as they provide better results than do object detection networks in occlusion situations. Experimental results are obtained with public datasets to show the feasibility of the solution.