As part of the early warning system, forest fire detection has a critical role in detecting fire in a forest area to prevent damage to forest ecosystems. In this case, the speed of the detection process is the most critical factor to support a fast response by the authorities. Thus, this article proposes a new framework for fire detection based on combining color-motion-shape features with machine learning technology. The characteristics of the fire are not only red but also from their irregular shape and movement that tends to be constant at specific locations. These characteristics are represented by color probabilities in the segmentation stage, color histograms in the classification stage, and image moments in the verification stage. A frame-based evaluation and an intersection over union (IoU) ratio was applied to evaluate the proposed framework. Frame-based evaluation measures the performance in detecting fires. In contrast, the IoU ratio measures the performance in localizing the fires. The experiment found that the proposed framework produced 89.97% and 10.03% in the true-positive rate and the false-negative rate, respectively, using the VisiFire dataset. Meanwhile, the proposed method can obtain an average of 21.70 FPS in processing time. These results proved that the proposed method is fast in the detection process and can maintain performance accuracy. Thus, the proposed method is suitable and reliable for integrating into the early warning system.

Image-based surveillance systems are widely employed toward safety and security applications in many fields. Cameras, that are connected over an IP network for monitoring public areas, can produce large quantities of video footage. It is tedious for humans to simultaneously observe every type of event on several cameras. Thus, it is necessary to build a userfriendly intelligent system, enabling the analysis of video to detect suspicious events. One of the most important tasks of this system would be to identify unattended objects to prevent an unexpected accident such as the bombing of a public space. This paper presents a novel technique for such a task. The method is based on a sequence of dual background differences, which is obtained by computing the intensity difference between the current and reference background models within a time period. A clustering and object detector are then integrated to identify the unattended objects. The effectiveness of method was verified using public and our own databases. The results confirmed that the method is efficient to detect unattended objects and is suitable for implementation in video surveillance systems.

In intelligent transportation systems, vehicle speed estimation plays a vital role in traffic monitoring, speed enforcement, and autonomous vehicles. Therefore, the authors propose a vehicle speed estimation method composed of pipelines: homography transformation using a deep image homography transformation network, vehicle detection by YOLOv8, tracking by ByteTrack, and speed estimation in consecutive frames. Homography transformation is utilized to rectify the monocular video view image into a bird’s-eye view with a constant pixel-per-meter value. In this scheme, the authors propose a method for estimating the speed in consecutive frames using statistical and machine learning approaches by comparing several experimental schemes to determine which method is better for estimating vehicle speed, such as vehicle speed estimation results in Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), traffic conditions, vehicle directions, and state-of-the-art studies. A monocular video DeaSpeedDataset was generated to evaluate the proposed system method by comparing the predicted speed value to the ground truth value obtained by the speed gun. This dataset has 2408 vehicles divided into 20 conditions, four setups, and two locations. Furthermore, the best RMSE was approximately 2.37897 km/h, and the MAE was approximately 1.68977 km/h.

As one of the essential modules in intelligent surveillance systems, loitering detection plays an important role in reducing theft incidents by analyzing human behavior. This paper introduces a novel strategy for detecting the loitering activities of humans in the monitoring area for an intelligent surveillance system based on a vision sensor. The proposed approach combines spatial and temporal information in the feature extraction stage to decide whether the human movement can be regarded as loitering. This movement has been previously tracked using human detectors and particle filter tracking. The proposed method has been evaluated using our dataset consisting of 20 videos. The experimental results show that the proposed method could achieve a relatively good accuracy of 85% when utilizing the random forest classifier in the decision stage. Thus, it could be integrated as one of the modules in an intelligent surveillance system.

This paper presents fire segmentation annotation data on 12 commonly used and publicly available “VisiFire Dataset” videos from http://signal.ee.bilkent.edu.tr/VisiFire/. This annotations dataset was obtained by per-frame, manual hand annotation over the fire region with 2684 total annotated frames. Since this annotation provides per-frame segmentation data, it offers a new and unique fire motion feature to the existing video, unlike other fire segmentation data that are collected from different still images. The annotations dataset also provides ground truth for segmentation task on videos. With segmentation task, it offers better insight on how well a machine learning model understood, not only detecting whether a fire is present, but also its exact location by calculating metrics such as Intersection over Union (IoU) with this annotations data. This annotations data is a tremendously useful addition to train, develop, and create a much better smart surveillance system for early detection in high-risk fire hotspots area.