Technology


Novel autonomous vehicle detection system uses deep learning


Autonomous vehicles require object-detection systems to navigate traffic and avoid obstacles. However, current methods often suffer from diminished detection capabilities in bad weather, on unstructured roads, or by occlusion. Now, a team of researchers from Korea have developed a novel IoT-enabled deep-learning type end-to-end 3D object detection system with improved detection capabilities even in poor environmental conditions. “Our system operates in real time, enhancing the object-


detection capabilities of autonomous vehicles, making navigation through traffic smoother and safer,” said Professor Gwanggil Jeon from the Department of Embedded Systems Engineering at Incheon National University (INU). Currently, autonomous vehicles use smart sensors like LiDAR


(light detection and ranging) for a 3D view of their surroundings and depth information, radar (radio detection and ranging) for detecting objects at night and cloudy weather, and a set of cameras for providing RGB images and a 360-degree view – all collectively forming a comprehensive dataset known as “point cloud”. However, these sensors often face challenges like reduced detection capabilities in adverse weather, on certain type of roads, or because of occlusions. The INU approach is built on the YOLO (‘You Only Look Once’)


v3 deep-learning object-detection technique, which is the most active state-of-the-art technique available for 2D visual detection.


Autonomous vehicles require object-detection systems to safely navigate traffic


The researchers first used the YOLOv3 technique to detect 2D objects and then modified it for 3D objects. Using both point-cloud data and RGB images as input, this system generates bounding boxes with high confidence, and labels visible obstacles as output, with overall accuracy of 97%. “By improving detection capabilities, this system could propel


autonomous vehicles into the mainstream. The introduction of autonomous vehicles has the potential to transform the transportation and logistics industry, offering economic benefits through reduced dependence on human drivers and the introduction of more-efficient transportation methods,” said Jeon.


Insight SiP’s RF module connects the eCelsius Performance System


French MedTech BodyCAP has developed a pioneering eCelsius Performance Connect System, centred on a connected ingestible thermometer for healthcare and wellbeing. It connects to smartphones and tablets via Insight SiP’s ISP1807-LR RF module, enabling continuous monitoring of core body temperature. Te ISP1807-LR module was chosen for its high memory capacity and flexible I/O set. Te thermometer is fitted into a capsule, which is swallowed. It


then monitors and measures the core body temperature as it passes through the gastrointestinal tract until it is expelled, a process that takes up to six days. BodyCAP’s device uses a 2cm ingestible capsule, which is accurate


to ±0.1ºC and uses a secure communications protocol. Te ingested capsule transmits information via a sub-GHz radio to a wearable watch-type device called ePerf Connect. Tis in turn relays data via Bluetooth that can be read by any compatible system, like a smartphone or a tablet. Te ingested capsule relays information in real time every 15


seconds to the ePerf Connect, which records the data and triggers alerts if a threshold temperature is exceeded.


Bluetooth connectivity is provided by the ISP1807-LR


RF module. Renowned for its compact size and low power consumption, this module is the backbone of the ePerf Connect device’s connectivity. Its small size ensures unobtrusive integration, whilst its lower power consumption extends the operational life of the ePerf Connect, making it a reliable and long-lasting solution. Te module offers a Bluetooth-5 stack, which provides long


range, high throughput and improved coexistence, along with IPv6 connectivity and Mesh capabilities. “Insight SiP’s RF module is ideal for the connectivity of


the eCelsius System, a complex application, requiring fast, reliable processing and best-in-class power consumption. The module’s small size makes it ideal for our wearable gateway product, and its sophisticated features allow it to form the core of this product. Our system is a breakthrough for research and medical applications in which measuring core body temperature is key to diagnosis and finding the best solutions for patients,” said Sébastien Moussay, Co-Founder and Chairman of BodyCAP.


www.electronicsworld.co.uk April 2024 05


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44