On-Board Crowd Counting and Density Estimation Using Low Altitude Unmanned Aerial Vehicles-Looking beyond Beating the Benchmark

Article Construction & Building Technology

Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies

Yuhan Jiang et al.

Summary: This paper proposes a method for object and defect detection using drones and cameras to collect 3D point clouds, and utilizing U-Net for segmentation. Experimental results show that U-Net with multiple features outperforms single-feature methods, improving accuracy and efficiency in inspection, assessment, and management of buildings and infrastructural facilities.

JOURNAL OF PERFORMANCE OF CONSTRUCTED FACILITIES (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Pruning and quantization for deep neural network acceleration: A survey

Tailin Liang et al.

Summary: Deep neural networks have been widely used in computer vision applications, but their complex architectures pose challenges in real-time deployment due to high computation resources and energy costs. Network compression techniques such as pruning and quantization can help overcome these challenges by reducing redundant computations. Both techniques can be used independently or together to improve the efficiency and performance of deep neural networks.

NEUROCOMPUTING (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Approaches on crowd counting and density estimation: a review

Bo Li et al.

Summary: In recent years, the need for counting crowds and vehicles has driven research in crowd counting and density estimation, with deep learning techniques greatly improving counting performance and expanding application scenarios. This study introduces and analyzes typical methods in the field, focusing particularly on deep learning-based counting methods. The challenges and solutions faced by crowd counting are summarized, along with proposed development trends for the future.

PATTERN ANALYSIS AND APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization

Qi Wang et al.

Summary: In the past decade, crowd counting and localization have gained much attention from researchers due to their wide range of applications. The NWPU-Crowd dataset is constructed to address the issue of small-scale datasets, containing a large number of annotated heads with points and boxes. A benchmark website is developed for impartial evaluation of different methods, providing researchers with a platform to submit test results and analyze new challenges in the field.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods

A Study on UAV Operating System Security and Future Research Challenges

Shahrear Iqbal

Summary: The popularity of Unmanned Aerial Vehicles (UAVs) is increasing across various industries, but they also face numerous security challenges. To ensure the safety of UAVs, an intelligent and automated defense mechanism integrated within the operating system is necessary. Further research is needed to address the security issues and develop a secure operating system for UAVs.

2021 IEEE 11TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC) (2021)

添加到收藏夹

Article Imaging Science & Photographic Technology

Critical Aspects of Person Counting and Density Estimation

Roland Perko et al.

Summary: This paper explores person counting and density estimation tasks using convolutional neural networks (CNNs), identifying critical problems and proposing solutions to improve accuracy significantly compared to baseline methods. This provides a deeper understanding of CNN-based person density estimation and highlights current limitations in evaluation protocols for advancing the field.

JOURNAL OF IMAGING (2021)

添加到收藏夹

Article Computer Science, Information Systems