An early fire detection in indoor environment is essential for people’s safety. During the past few years, many approaches using image processing and computer vision techniques were proposed. However, it is still a challenging task for application of video smoke detection in indoor environment, because the limitations of data for training and lack of efficient algorithms. The purpose of this paper is to present a new smoke detection method by using surveillance cameras. The proposed method is composed of two stages. In the first stage, motion regions between consecutive frames are located by using optical flow. In the second stage, a deep convolutional neural network is used to detect smoke in motion regions. Besides, to overcome the problem of lacking data, simulated smoke images are used to enrich the dataset. The proposed method is tested on our data set and real video sequences. Experiments show that the new method is successfully applied to various indoor smoke videos and significant for improving the accuracy of fire smoke detection. Source code and the dataset have been made available online.

This paper addresses the problem of lane detection which is fundamental for self-driving vehicles. Our approach exploits both colour and depth information recorded by a single RGB-D camera to better deal with negative factors such as lighting conditions and lane-like objects. In the approach, colour and depth images are first converted to a half-binary format and a 2D matrix of 3D points. They are then used as the inputs of template matching and geometric feature extraction processes to form a response map so that its values represent the probability of pixels being lane markers. To further improve the results, the template and lane surfaces are finally refined by principal component analysis and lane model fitting techniques. A number of experiments have been conducted on both synthetic and real datasets. The result shows that the proposed approach can effectively eliminate unwanted noise to accurately detect lane markers in various scenarios. Moreover, the processing speed of 20 frames per second under hardware configuration of a popular laptop computer allows the proposed algorithm to be implemented for real-time autonomous driving applications.

Simultaneous localization and mapping (SLAM) is essential for unmanned aerial vehicle (UAV) applications since it allows the UAV to estimate not only its position and orientation but also the map of its working environment. We propose in this study a new SLAM system for UAVs named SupSLAM that works with a stereo camera and an inertial measurement unit (IMU). The system includes a front-end that provides an initial estimate of the UAV position and working environment and a back-end that compensates for the drift caused by the initial estimation. To improve the accuracy and robustness of the system, we use a new feature extraction method named SuperPoint, which includes a pretrained deep neural network to detect key points for estimation. This method is not only accurate in feature extraction but also efficient in computation so that it is relevant to implement on UAVs. We have conducted a number of experiments and comparisons to evaluate the performance of the proposed system. The results show that the system is feasible for UAV SLAM with the performance comparable to state-of-art methods in most datasets and better in some challenging conditions.

In this work, we propose a new approach that combines data from multiple sensors for reliable obstacle avoidance. The sensors include two depth cameras and a LiDAR arranged so that they can capture the whole 3D area in front of the robot and a 2D slide around it. To fuse the data from these sensors, we first use an external camera as a reference to combine data from two depth cameras. A projection technique is then introduced to convert the 3D point cloud data of the cameras to its 2D correspondence. An obstacle avoidance algorithm is then developed based on the dynamic window approach. A number of experiments have been conducted to evaluate our proposed approach. The results show that the robot can effectively avoid static and dynamic obstacles of different shapes and sizes in different environments.

This paper introduces a system to monitor agriculture fields in real time. It includes a sensor network for in situ data collection and an unmanned aerial vehicle (UAV)) system for remote sensing. The sensor network uses a number of sensor nodes to measure different parameters of the plants and environment such as temperature, humidity, and nitrogen composition. For data communication, the sensor network uses LoRa, a low-power wide-area network modulation technique, that allows receiving signals from sensor nodes at a distance of up to 450 m for a single receiver. The UAV includes visual and near infrared cameras to collect photos of the field. The data collection is carried out automatically via a path planning process that takes into account the overlapping ratio and resolution of the photos. The data collected is then handled by a cloud server that allows users to access in real time via a web-based application and an application on smartphones. A number of experiments have been conducted with the system being tested in several agricultural sites to evaluate its practical applicability.