Road intersection data have been used across a range of geospatial analyses. However, many datasets dating from before the advent of GIS are only available as historical printed maps. To be analyze...

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

Road intersections data have been used across different geospatial applications and analysis. The road network datasets dating from pre-GIS years are only available in the form of historical printed maps. Before they can be analyzed by a GIS software, they need to be scanned and transformed into the usable vector-based format. Due to the great bulk of scanned historical maps, automated methods of transforming them into digital datasets need to be employed. Frequently, this process is based on computer vision algorithms. However, low conversion accuracy for low quality and visually complex maps and setting optimal parameters are the two challenges of using those algorithms. In this paper, we employed the standard paradigm of using deep convolutional neural network for object detection task named region-based CNN for automatically identifying road intersections in scanned historical USGS maps of several U.S. cities. We have found that the algorithm showed higher conversion accuracy for the double line cartographic representations of the road maps than the single line ones. Also, compared to the majority of traditional computer vision algorithms RCNN provides more accurate extraction. Finally, the results show that the amount of errors in the detection outputs is sensitive to complexity and blurriness of the maps as well as the number of distinct RGB combinations within them.

Recommender systems (RS), as supportive tools, filter information from a massive amount of data based on the determined preferences. Most of the RS require information about the context of users su...

Improvement of a location-aware recommender system using volunteered geographic information

This paper analyzes the development status of intelligent tourist guide system and studies Apriori-based association rule algorithm with corresponding improvement. Then this paper puts forward a weighted association rule algorithm. The algorithm comprehensively takes in to account nature, behavior and situation of tourists, to put forward three aspects of improvement in defects of efficiency and accuracy according to Apriori algorithm and it further establishes the improved tourists' behavior-preference model. On this basis, we construct personalized tourists' area recommendation model, and analyzes the instance data with data mining, to verify the accuracy in recommending framework, achieving more effective personalized scenic spot recommendation strategy.

Intelligent Recommendation Scheme of Scenic Spots Based on Association Rule Mining Algorithm

Object tracking is a computer vision problem that gained attention in the past few decades. Numerous algorithms targeting various challenges associated with object tracking have been proposed to address issues related to multiple objects tracking, handling complex scenarios like fog and occlusions, and other subproblems within the object tracking area. On the other hand, the extensive use of Unmanned Aerial Vehicles (UAVs) or Drones is increasing exponentially all around the world for a variety of applications. Object tracking using drones has an enormous number of applications, especially in smart transportation system. In this paper, we present a lightweight infrastructure-less object tracking system and assess its performance using the VICON motion capture system. The performance results obtained was very close to that of the optimal infrastructure-based solution.

Object Tracking Framework for Unmanned Aerial Vehicles

Identifying and detecting the different objects in an image is important skill in computer vision. Fast and reliable object detection is significant approach for interacting with one's environment. Human uses a process called as visual attention to quickly decide which location of an image need to be processed in detail and which can be ignored. But for the machine it is difficult task to identify object and exact location of the object in an image. To overcome this difficulty machine learning and deep learning have made great progress with the help of algorithm series based on R-CNN. This algorithm series have given amazing results with the help of some wellknown datasets like Image-Net, Pascal voc, coco etc.

/pdf/a-review-object-detection-using-deep-learning-2qaejtffs0.pdf

A Review: Object Detection using Deep Learning

In the tourism recommendation system, the number of users and items is very large. But traditional recommendation system uses partial information for identifying similar characteristics of users. Collaborative filtering is the primary approach of any recommendation system. It provides a recommendation which is easy to understand. It is based on similarities of user opinions like rating or likes and dislikes. So the recommendation provided by collaborative cannot be considered as quality recommendation. Recommendation after association rule mining is having high support and confidence level. So that will be considered as strong recommendation. The hybridization of both collaborative filtering and association rule mining can produce strong and quality recommendation even when sufficient data are not available. This paper combines recommendation for tourism application by using a hybridization of traditional collaborative filtering technique and data mining techniques.

/pdf/a-modified-approach-towards-tourism-recommendation-system-4th51lqinn.pdf

Monali R. Gandhi

Papers

A Review: Object Detection using Deep Learning

A Modified Approach towards Tourism Recommendation System with Collaborative Filtering and Association Rule Mining