No abstract

In regular convolutional neural networks (CNN), fully-connected layers act as classifiers to estimate the probabilities for each instance in classification tasks. The accuracy of CNNs can be improved by replacing fully connected layers with gradient boosting algorithms. In this regard, this study investigates three robust classifiers, namely XGBoost, LightGBM, and Catboost, in combination with a CNN for a land cover study in Hanoi, Vietnam. The experiments were implemented using SPOT7 imagery through (1) image segmentation and extraction of features, including spectral information and spatial metrics, (2) normalization of attribute values and generation of graphs, and (3) using graphs as the input dataset to the investigated models for classifying six land cover classes, namely House, Bare land, Vegetation, Water, Impervious Surface, and Shadow. The results show that CNN-based XGBoost (Overall accuracy = 0.8905), LightGBM (0.8956), and CatBoost (0.8956) outperform the other methods used for comparison. It can be seen that the combination of object-based image analysis and CNN-based gradient boosting algorithms significantly improves classification accuracies and can be considered as alternative methods for land cover analysis.

Spatial information technology has been widely used for vehicles in general and for fleet management. Many studies have focused on improving vehicle positioning accuracy, although few studies have focused on efficiency improvements for managing large truck fleets in the context of the current complex network of roads. Therefore, this paper proposes a multilayer-based map matching algorithm with different spatial data structures to deal rapidly with large amounts of coordinate data. Using the dimension reduction technique, the geodesic coordinates can be transformed into plane coordinates. This study provides multiple layer grouping combinations to deal with complex road networks. We integrated these techniques and employed a puncture method to process the geometric computation with spatial data-mining approaches. We constructed a spatial division index and combined this with the puncture method, which improves the efficiency of the system and can enhance data retrieval efficiency for large truck fleet dispatching. This paper also used a multilayer-based map matching algorithm with raster data structures. Comparing the results revealed that the look-up table method offers the best outcome. The proposed multilayer-based map matching algorithm using the look-up table method is suited to obtaining competitive performance in identifying efficiency improvements for large truck fleet dispatching.

Transportation safety has been widely discussed for avoiding forward collisions. The broad concept of remote sensing can be applied to detect the front of vehicles without contact. The traditional Haar features use adjacent rectangular areas for many ordinary vehicle studies to detect the front vehicle images in practice. This paper focused on large vehicles using a front-installed digital video recorder (DVR) with a near-infrared (NIR) camera. The views of large and ordinary vehicles are different; thus, this study used a deep learning method to process progressive improvement in moving vehicle detection. This study proposed a You Only Look Once version 4 (YOLOv4) supplemented with the fence method, called YOLOv4(III), to enhance vehicle detection. This method had high detection accuracy and low false omission rates using the general DVR equipment, and it provided comparison results. There was no need to have a high specification front camera, and the proposed YOLOv4(III) was found to have competitive performance. YOLOv4(III) reduced false detection rates and had a more stable frame per second (FPS) performance than with Haar features. This improved detection method can give an alert for large vehicle drivers to avoid serious collisions, leading to a reduction in the waste of social resources.

Mazu, a protective sea God, has been worshipped by residents of Taiwan and southeast coast of mainland China as well as overseas Chinese around the globe for hundreds of years. The number of people around the world under her influence of religious belief and moral culture can reach up hundreds of million. Every year in lunar March, the over- one-week long Mazu patrol and pilgrimage held by Jenn Lann Temple in Dajia County of Taiwan attracts millions of pilgrims and tourists around the world to participate in one of the biggest religious events in the world. To keep track of the entire patrol and pilgrimage, Jenn Lann Temple has been cooperating with GIS Research Center, Feng-Chia University since 2008, setting up a GPS receiver, a digital camera, and 4 video recorders on Mazu’s palanquin. Both real-time position of the palanquin and live videos on the scene along the way of pilgrimage were published on the Internet, providing pilgrims, tourists and viewers around the world with an open access to observe the entire event. This paper details this initiative of introducing spatial technology to large cultural events. The study collects the historic tracks of Mazu’s palanquin during the pilgrimage from 2008 to 2010, analyzes their spatial-temporal attributes, and elicits several interesting facts behind the figures and maps. It also explores how spatial technologies can help organize large-scale events and even accelerate the dissemination of culture