Naim Dahnoun

This study explored an indoor system for tracking multiple humans and detecting falls, employing three Millimeter-Wave radars from Texas Instruments. Compared to wearables and camera methods, Millimeter-Wave radar is not plagued by mobility inconveniences, lighting conditions, or privacy issues. We conducted an initial evaluation of radar characteristics, covering aspects such as interference between radars and coverage area. Then, we established a real-time framework to integrate signals received from these radars, allowing us to track the position and body status of human targets non-intrusively. Additionally, we introduced innovative strategies, including dynamic Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering based on signal SNR levels, a probability matrix for enhanced target tracking, target status prediction for fall detection, and a feedback loop for noise reduction. We conducted an extensive evaluation using over 300 min of data, which equated to approximately 360,000 frames. Our prototype system exhibited a remarkable performance, achieving a precision of 98.9% for tracking a single target and 96.5% and 94.0% for tracking two and three targets in human-tracking scenarios, respectively. Moreover, in the field of human fall detection, the system demonstrates a high accuracy rate of 96.3%, underscoring its effectiveness in distinguishing falls from other statuses.

Applications for millimeter-wave (mmWave) radars have become increasingly popular in human activity recognition. Many researchers have combined radars with neural networks and gained a high performance on various applications. However, most of these studies feed the raw point cloud data directly into the networks, which can be unstable and inaccurate under certain circumstances. In this paper, we define a reliability measure of the point cloud data and design a novel voxelization algorithm to reconstruct the data. Experiments show that our algorithm can improve the stability of the point cloud generated from mmWave radars in terms of error reduction and scene re-construction. We demonstrate the effectiveness of our proposed algorithm using a neural network-based system for identifying a person’s sitting direction. In our experiment, compared with the baseline, our voxelization algorithm can improve the system in terms of accuracy (4.3%), training time (55.6%), and computational complexity, which is more suitable for light-weighted networks and low energy consumption platforms.

Various 3D reconstruction methods have enabled civil engineers to detect damage on a road surface. To achieve the millimetre accuracy required for road condition assessment, a disparity map with subpixel resolution needs to be used. However, none of the existing stereo matching algorithms are specially suitable for the reconstruction of the road surface. Hence in this paper, we propose a novel dense subpixel disparity estimation algorithm with high computational efficiency and robustness. This is achieved by first transforming the perspective view of the target frame into the reference view, which not only increases the accuracy of the block matching for the road surface but also improves the processing speed. The disparities are then estimated iteratively using our previously published algorithm where the search range is propagated from three estimated neighbouring disparities. Since the search range is obtained from the previous iteration, errors may occur when the propagated search range is not sufficient. Therefore, a correlation maxima verification is performed to rectify this issue, and the subpixel resolution is achieved by conducting a parabola interpolation enhancement. Furthermore, a novel disparity global refinement approach developed from the Markov Random Fields and Fast Bilateral Stereo is introduced to further improve the accuracy of the estimated disparity map, where disparities are updated iteratively by minimising the energy function that is related to their interpolated correlation polynomials. The algorithm is implemented in C language with a near real-time performance. The experimental results illustrate that the absolute error of the reconstruction varies from 0.1 mm to 3 mm.

Achieving high-resolution time-to-digital conversion is challenging at high count rates. In past work, the highest resolutions with low dead times (≤2 cycles) on field-programmable gate arrays (FPGAs) have been achieved using digital signal processing (DSP) blocks or using the wave-union method. In this article, we investigate the possibility of combining the wave-union method with DSP blocks. With the given configuration on a Xilinx Artix-7 200T FPGA, we achieve 13.60-ps single-shot precision (SSP) using only 3.78% of the FPGA fabric per channel (1.22% of the fabric in the finite step response (FSR) injector and 2.56% of the fabric in the delay line) for three edges, compared to 52.65 ps using 2.97% of the FPGA fabric per channel without the wave-union method. The scaling of edge numbers (for higher resolutions) is shown to be significantly better than the previously suggested parallel implementation, at just 0.407% of the FPGA fabric per edge compared to ~2.5% per edge in the parallel implementation. Temperature characterization showed an SSP penalty of just 4 ps over a 60 °C temperature difference.

Millimetre-wave (mmWave) radar is increasing in popularity for human activity recognition, due to its advantages of high resolution, non-intrusive nature and suitability for various environments. In this paper, we present a novel human posture estimation system using mmWave radars. The system detects people with arbitrary postures in indoor environments at close distances (within two metres), and estimates the posture by localising the key joints. We use two mmWave radars to capture the scene and a neural network model to estimate the posture. The neural network model consists of a part detector that estimates the subject’s joint positions, and a spatial model that learns the correlation between the joints. A temporal correlation step is introduced to further refine the estimate when in real-time operation. The system can provide an accurate posture estimate of the person in real-time at 20 fps, with a mean localisation error of 12.2 cm and an average precision of 71.3%.

Teaching electronics is not only for electrical and electronics students but also for mechanical, aerospace, engineering design, civil and engineering mathematics programmes, which are likely to have electronics units as part of their curriculum. To teach electronics for these non-electronic programmes is very challenging in many aspects. First, the electronics unit has to satisfy the learning outcomes for each programme. Second, the student’s motivation is normally very low since electronics is not the career the students would like to pursue. Third, the timetabling can be an issue when a large number of students are enrolled; for instance, at the University of Bristol, over 340 students are registered for the electronics unit. Due to this large number and the capacity of the electrical laboratory, students will have laboratory experiments timetabled in different weeks and some may have laboratory experiments before the lectures are covered. Finally, a method of assessing this large number of students has to be put into place. In this paper, the content of the unit including the laboratory experiments, the methods of course delivery and the assessment methods are justified. Also, since students learn differently and have a variety of motivations, a combination of teaching methods has to be found to satisfy more students and improve the learning outcomes.

Accurate calculation of a disparity map in real-time is a challenge in computer vision and autonomous applications due to the expensive computation cost. This paper describes a local temporal stereo method, using normalized cross correlation (NCC) as the matching cost function. To increase the performance in terms of speed without degrading the quality, a down sampling of the disparity map in the y-axis has been used, with a restricted search range along the y-axis. In addition to these, the search range is further restricted by referencing the disparity map from the previous frames. The algorithm is evaluated on a Texas Instruments (TI) KeyStone II embedded SoC with four ARM cores and eight DSP cores. The application has been written using OpenMP, OpenCL and IPC/MessageQ for parallelising the program. The core of the application has been optimised for this specific platform using linear assembly code in order to take advantage of SIMD instructions available with the DSP. The application achieved 77 FPS on a 1242×375 resolution video with 80 disparity levels using one ARM core and eight DSP cores.