Smoke detection is a key component of disaster and accident detection. Despite the wide variety of smoke detection methods and sensors that have been proposed, none has been able to maintain a high frame rate while improving detection performance. In this paper, a smoke detection method for surveillance cameras is presented that relies on shape features of smoke regions as well as color information. The method takes advantage of the use of a stationary camera by using a background subtraction method to detect changes in the scene. The color of the smoke is used to assess the probability that pixels in the scene belong to a smoke region. Due to the variable density of the smoke, not all pixels of the actual smoke area appear in the foreground mask. These separate pixels are united by morphological operations and connected-component labeling methods. The existence of a smoke region is confirmed by analyzing the roughness of its boundary. The final step of the algorithm is to check the density of edge pixels within a region. Comparison of objects in the current and previous frames is conducted to distinguish fluid smoke regions from rigid moving objects. Some parts of the algorithm were boosted by means of parallel processing using CUDA GPUs, thereby enabling fast processing of both low-resolution and high-definition videos. The algorithm was tested on multiple video sequences and demonstrated appropriate processing times for a realistic range of frame sizes.

Cranes play an important role in the industry sectors worldwide, such as construction, transport, shipping and cargo industry. For the safety of loading and unloading materials there are definitely ongoing improvements in the crane industry. However, there still remains issues related to the crane operation and control measures given by the pendulum swing while the crane is moving. To solve this problem a vision-based movement control of a 3 degrees of freedom (3 DOF) crane system, using both an analytical and experimental models based on displacements and adaptive optimization algorithms was proposed. The framework consists of three steps, more precise recognition, detection and tracking a set of targets within the image to compute the payload displacement. A prepossessing process was applied in order to enhance the image improving both the color information and the edge extraction task. Then, a set of targets within the image were detected to estimate the displacement. Then to solve the problem given by the displacement, a tracking task was implemented using a second order filter. This paper introduces a new strategy to determine the relationship between the movement of the spin in the jib and position of the markers within the image. Regression analysis was carried out to take into account the motion of the cart and the payload. In Results Section is shown a set of real-time experiment, obtaining euclidean errors of 1.41 pixel, 2 pixels and 3.16 pixels for Cart, Jib and Hoist, respectively.

Fruit quality assessment is vital for ensuring consumer satisfaction and marketability in agriculture. This study explores deep learning techniques for assessing fruit quality, focusing on practical deployment in resource-constrained environments. Two approaches were compared: training a convolutional neural network (CNN) from scratch and fine-tuning a pre-trained MobileNetV2 model through transfer learning. The performance of these models was evaluated using a subset of the Fruits-360 dataset chosen to simulate real-world conditions for small-scale producers. MobileNetV2 was selected for its compact size and efficiency, suitable for devices with limited computational resources. Both approaches achieved high accuracy, with the transfer learning model demonstrating faster convergence and slightly better performance. Feature map visualizations provided insight into the model’s decision-making, highlighting damaged areas of fruits which enhances transparency and trust for end users. This study underscores the potential of deep learning models to modernize fruit quality assessment, offering practical, efficient, and interpretable tools for small-scale farmers.

In this paper we propose to detect the localization and recognition of outdoor stairway. This problem is the most fundamental step in solving the problem of autonomous stair climbing navigation. An autonomous system must be able to recognize parameters that can describe stairways in unknown environments. First, we proposed to extract the longest segments of diagonal lines from the edge image in order to identify a set of diagonal line segments candidate. This can provide information itself. Based on the vanishing point we defined the area where the stair candidate is located. We then applied the Gabor filter to detect the horizontal line. Finally, after combining the previous two steps, the algorithm defined the candidate stair area in the image. A set of stair images were used within a variety of conditions in our proposed method. As a result, testing was able to prove its effectiveness.

This paper describes a car detection method by combining data obtained from a laser and a camera. Data from the camera and the laser range finder (LRF) are combined after a calibration method has been performed. The calibration method defines the relative pose between camera and LRF. Car candidates are then extracted from the LRF data. The car candidate regions on the image are generated based on the filtered LRF data based on its size. To filter out the bad candidates, a verification method is performed on the car candidate regions. This method eliminates the needs of checking over several positions and scales, enables a speed enhancement over the general object detection strategy.