Entropy-Based Ultra-Wide Band Radar Signals Segmentation for Multi Obstacle Detection

Mimouna, Amira; Khalifa, Anouar Ben; Alouani, Ihsen; Amara, Najoua Essoukri Ben; Rivenq, Atika; Taleb‐Ahmed, Abdelmalik

doi:10.1109/jsen.2021.3050054

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the farmland environment is open, there are often multiple obstacles, and single obstacle detection cannot effectively detect all obstacles, which will bring security risks to farmland operations. At present, multi-obstacle detection technology is mainly used in the field of automatic driving of automobiles, and it is used less in agriculture [1,2]. In order to ensure the safe driving and operation of unmanned agricultural machines, multi-obstacle detection technology is essential.…”

Section: Introductionmentioning

confidence: 99%

“…(1) Obstacles are only detected and located, but obstacles cannot be identified and classified, which is disadvantageous to the accurate path planning and obstacle avoidance of agricultural robots or unmanned agricultural vehicles. (2) The types and number of detected obstacles are limited, and if the selected features are not enough to represent the target obstacle, the missed or fail detection rate will be increased.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering

Xue

Feng

et al. 2022

Sensors

View full text Add to dashboard Cite

It is necessary to detect multi-type farmland obstacles in real time and accurately for unmanned agricultural vehicles. An improved YOLOv5s algorithm based on the K-Means clustering algorithm and CIoU Loss function was proposed to improve detection precision and speed up real-time detection. The K-Means clustering algorithm was used in order to generate anchor box scales to accelerate the convergence speed of model training. The CIoU Loss function, combining the three geometric measures of overlap area, center distance and aspect ratio, was adopted to reduce the occurrence of missed and false detection and improve detection precision. The experimental results showed that the inference time of a single image was reduced by 75% with the improved YOLOv5s algorithm; compared with that of the Faster R-CNN algorithm, real-time performance was effectively improved. Furthermore, the mAP value of the improved algorithm was increased by 5.80% compared with that of the original YOLOv5s, which indicates that using the CIoU Loss function had an obvious effect on reducing the missed detection and false detection of the original YOLOv5s. Moreover, the detection of small target obstacles of the improved algorithm was better than that of the Faster R-CNN.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%