Download PDFOpen PDF in browser

APH-Yolov7t: Yolov7-Tiny with Attention Prediction Head for Person Detection on Drone-Captured Search and Rescue Scenarios

EasyChair Preprint no. 11184

13 pagesDate: October 27, 2023


Inspection and intervention by drones in rescue operations have growing attention due to multiple causes, including natural and man-related events. Additionally, the rapid advancements in vision sensors, object detection models, and AI-based methods can boost the success of rescue scenarios. Drone navigation involves object scale variations creating a computation load and densely packed objects in the scene urge high-speed processing. To solve the two issues mentioned above, we propose the APH- Yolov7t method. In this paper, we introduce a new Attention-based Prediction Head for Yolov7-tiny. We also present the evaluation results of Yolov7 the latest state-of the-art convolutional neural network-based solution, here is used for robust object detection in the context of drone navigation to perform detection of persons on land and sea surfaces allowing to reduce disaster, distress, identify and rescue them. Despite the higher success rate of object detection models, vision complexities make detection tasks on drone-captured images more challenging and this area remains under-explored. We used the existing three search and rescue datasets which are images acquired from drones specific to our objective. Results show that our APH-Yolov7t method was the most robust attention-based Yolo and comprehensive object detection method for our application, demonstrating a consistently high level of performance in comparison to Yolov7-tiny. Evaluation results on all three datasets are reported. With this solution, we demonstrate to be able to satisfy our requirements of a mean average precision (mAP50) of over 0.80 for the person class and operational performance with over 125fps on a single GPU Nvidia RTX2080Ti.

Keyphrases: attention-head, drone datasets, evaluation, fine-tuning, object detection, person class, YOLOv7

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Vamshi Kodipaka and Lino Forte Marques and Helder Jesus Araújo and Rui Pedro Duarte Cortesão},
  title = {APH-Yolov7t: Yolov7-Tiny with Attention Prediction Head for Person Detection on Drone-Captured Search and Rescue Scenarios},
  howpublished = {EasyChair Preprint no. 11184},

  year = {EasyChair, 2023}}
Download PDFOpen PDF in browser