Tourist Mobility Patterns: Faster R-CNN Versus YOLOv7 for Places of Interest Detection

Abstract

The mobility of tourists plays a significant role in shaping their travel experiences and the overall dynamics of a destination. In recent years, the proliferation of social media platforms has provided a rich source of visual data, allowing us to leverage the abundance of pictures shared by tourists to extract meaningful information. Using computer vision techniques and deep learning algorithms, such as object detection, it becomes possible to extract useful information from tourist pictures. In this study, we look for the best way to detect objects from pictures shared by tourists during their journey in order to determine their locations. To achieve our goal we propose a new methodology composed by; database creation, database annotation, preprocessing, deep learning implementation and evaluation. We implemented two deep learning object detection methods: YOLOv7 and Faster R-CNN. A dataset has been created to provide examples of training and testing for neuronal networks. The training was performed on various basic models, in order to increase the efficiency of the training time and to compare the results. We evaluated the results using three parameters: precision, recall and mAP. The results indicate that YOLOv7 has the precision and performance, with over 90% mAP, 92.1% precision and 92.7% recall.

TourOptiGuide: A Hybrid and Personalized Tourism Recommendation System

“…Furthermore, certain systems incorporate multimodal data, such as textual descriptions of images or contextual information, to enhance the comprehension of point-of-interest content [36]. Our research indicates that Yolov8 outperforms other object detection algorithms in terms of accuracy and performance [37]. As result, we employ this algorithm in the first part of our suggested system to identify and locate things in travel photos.…”

“…The proposed POI detection mechanism can be used to help tourists to navigate around a region based on POIs detected in their current environment. Many researchers have recently proposed the use of neural network architectures [32][33][34], transfer learning [35], and advanced reinforcement techniques to improve the performance and accuracy of POI detection. Furthermore, certain systems incorporate multimodal data, such as textual descriptions of images or contextual information, to enhance the comprehension of point-of-interest content [36].…”

UAV Control Based on Pattern Recognition in Aquaculture Application

“…We can reduce one of their values as a cost to increase precision or recall rate. The area under the curve is AP, the equation is (9), and the larger the area, the better the result. The larger the area under the curve, the higher the precision and recall rate, and the easier it is for the model to detect the target.…”

“…The quicker and more accurate algorithm means it can be deployed on faster vehicles. Currently, more versions of YOLO are being presented, such as YOLOv7 and YOLOv8 [9,10]. These models can provide higher accuracy, but the structures are more complex and take more computing time, which is unsuitable for this study.…”