Search Results (5)

The analysis of infrared video images is becoming one of the methods used to detect thermal hazards in many large-scale engineering sites. The fusion of infrared thermal imaging and visible image data in the target area can help people to identify and locate the fault points of thermal hazards. Among them, a very important step is the registration of thermally visible images. However, the direct registration of images with large-scale differences may lead to large registration errors or even failure. This paper presents a novel two-stage thermal–visible-image registration strategy specifically designed for exceptional scenes, such as a substation. Firstly, the original image pairs that occur after binarization are quickly and roughly registered. Secondly, the adaptive downsampling unit partial-intensity invariant feature descriptor (ADU-PIIFD) algorithm is proposed to correct the small-scale differences in details and achieve finer registration. Experiments are conducted on 30 data sets containing complex power station scenes and compared with several other methods. The results show that the proposed method exhibits an excellent and stable performance in thermal–visible-image registration, and the registration error on the entire data set is within five pixels. Especially for multimodal images with poor image quality and many detailed features, the robustness of the proposed method is far better than that of other methods, which provides a more reliable image registration scheme for the field of fire safety. Full article

Various studies have been conducted on object detection, tracking, and action recognition based on thermal images. However, errors occur during object detection, tracking, and action recognition when a moving object leaves the field of view (FOV) of a camera and part of the object becomes invisible. However, no studies have examined this issue so far. Therefore, this article proposes a method for widening the FOV of the current image by predicting images outside the FOV of the camera using the current image and previous sequential images. In the proposed method, the original one-channel thermal image is converted into a three-channel thermal image to perform image prediction using an image prediction generative adversarial network. When image prediction and object detection experiments were conducted using the marathon sub-dataset of the Boston University-thermal infrared video (BU-TIV) benchmark open dataset, we confirmed that the proposed method showed the higher accuracies of image prediction (structural similarity index measure (SSIM) of 0.9839) and object detection (F1 score (F1) of 0.882, accuracy (ACC) of 0.983, and intersection over union (IoU) of 0.791) than the state-of-the-art methods. Full article

Because intelligent surveillance systems have recently undergone rapid growth, research on accurately detecting humans in videos captured at a long distance is growing in importance. The existing research using visible light cameras has mainly focused on methods of human detection for daytime hours when there is outside light, but human detection during nighttime hours when there is no outside light is difficult. Thus, methods that employ additional near-infrared (NIR) illuminators and NIR cameras or thermal cameras have been used. However, in the case of NIR illuminators, there are limitations in terms of the illumination angle and distance. There are also difficulties because the illuminator power must be adaptively adjusted depending on whether the object is close or far away. In the case of thermal cameras, their cost is still high, which makes it difficult to install and use them in a variety of places. Because of this, research has been conducted on nighttime human detection using visible light cameras, but this has focused on objects at a short distance in an indoor environment or the use of video-based methods to capture multiple images and process them, which causes problems related to the increase in the processing time. To resolve these problems, this paper presents a method that uses a single image captured at night on a visible light camera to detect humans in a variety of environments based on a convolutional neural network. Experimental results using a self-constructed Dongguk night-time human detection database (DNHD-DB1) and two open databases (Korea advanced institute of science and technology (KAIST) and computer vision center (CVC) databases), as well as high-accuracy human detection in a variety of environments, show that the method has excellent performance compared to existing methods. Full article

The space time image velocimetry (STIV) technique is presented and shown to be a useful tool for extracting river flow information non-intrusively simply by taking surface video images. This technique is applied to measure surface velocity distributions on the Uono River on Honshu Island, Japan. At the site, various measurement methods such as a radio-wave velocity meter, an acoustic Doppler current profiler (ADCP) or imaging techniques were implemented. The performance of STIV was examined in various aspects such as a night measurement using a far-infrared-ray (FIR) camera and a comparison to ADCP data for checking measurement accuracy. All the results showed that STIV is capable of providing reliable data for surface velocity and water discharge that agree fairly well with ADCP data. In particular, it was demonstrated that measurements during the night can be conducted without any difficulty using an FIR camera and the STIV technique. In particular, using the FIR camera, the STIV technique can capture water surface features better than conventional cameras even at low resolution. Furthermore, it was demonstrated that measurements during the night can be conducted without any difficulty. Full article

Far-infrared pedestrian detection approaches for advanced driver-assistance systems based on high-dimensional features fail to simultaneously achieve robust and real-time detection. We propose a robust and real-time pedestrian detection system characterized by novel candidate filters, novel pedestrian features and multi-frame approval matching in a coarse-to-fine fashion. Firstly, we design two filters based on the pedestrians’ head and the road to select the candidates after applying a pedestrian segmentation algorithm to reduce false alarms. Secondly, we propose a novel feature encapsulating both the relationship of oriented gradient distribution and the code of oriented gradient to deal with the enormous variance in pedestrians’ size and appearance. Thirdly, we introduce a multi-frame approval matching approach utilizing the spatiotemporal continuity of pedestrians to increase the detection rate. Large-scale experiments indicate that the system works in real time and the accuracy has improved about 9% compared with approaches based on high-dimensional features only. Full article