Search Results (8)

Advances in machine learning algorithms have allowed object detection and classification to become booming areas. The detection of objects, such as rocks, in mining operations is affected by fog, snow, suspended particles, and high lighting. These environmental conditions can stop the development of mining work, which entails a considerable increase in operating costs. It is vital to select a machine learning algorithm that is accurate, fast, and contributes to lower operational costs because of the aforementioned environmental situations. In this study, the Viola-Jones algorithm, Aggregate Channel Features (ACF), Faster Regions with Convolutional Neural Networks (Faster R-CNN), Single-Shot Detector (SSD), and You Only Look Once (YOLO) version 4 were analyzed, considering the precision metrics, recall, AP₅₀, and average detection time. In our preliminary tests, we have observed that the differences between YOLO v4 and the latest versions are not substantial for the specific problem of rock detection addressed in our article. Therefore, YOLO v4 is an appropriate and representative choice for evaluating the effectiveness of existing methods in our study. The YOLO v4 algorithm performed the best overall, whereas the SSD algorithm performed the fastest. The results indicate that the YOLO v4 algorithm is a promising candidate for detecting rocks with visual contamination in mining operations. Full article

Product recognition on grocery shelf images is a compelling task of object detection because of the similarity between products, the presence of the different scale of product sizes, and the high number of classes, in addition to constantly renewed packaging and added new products’ difficulty in data collection. The use of conventional methods alone is not enough to solve a number of retail problems such as planogram compliance, stock tracking on shelves, and customer support. The purpose of this study is to achieve significant results using the suggested multi-stage end-to-end process, including product detection, product classification, and refinement. The comparison of different methods is provided by a traditional computer vision approach, Aggregate Channel Features (ACF) and Single-Shot Detectors (SSD) are used in the product detection stage, and Speed-up Robust Features (SURF), Binary Robust Invariant Scalable Key points (BRISK), Oriented Features from Accelerated Segment Test (FAST), Rotated Binary Robust Independent Elementary Features (BRIEF) (ORB), and hybrids of these methods are used in the product classification stage. The experimental results used the entire Grocery Products dataset and its different subsets with a different number of products and images. The best performance was achieved with the use of SSD in the product detection stage and the hybrid use of SURF, BRISK, and ORB in the product classification stage, respectively. Additionally, the proposed approach performed comparably or better than existing models. Full article

Detection and classification of icebergs and ships in synthetic aperture radar (SAR) images play a vital role in marine surveillance systems even though available adaptive threshold methods give satisfying results on detection and classification for ships and icebergs, including techniques of convolutional neural networks (CNNs), but need more accuracy and precision. An efficient and accurate method was developed to detect and classify the ship and icebergs. Hence, the research method proposed locating and classifying both ships and icebergs in a given SAR image with the help of deep learning (DL) and non-DL methods. A non-DL method utilized here was the aggregate channel features (ACF) detector, which extracts region proposals from huge SAR images. The DL object detector called fast regions CNN (FRCNN) detects objects accurately from the result of ACF since the ACF method avoids unwanted regions. The novelty of this study was that ACF-FRCNN concentrates only on accurately classifying ships and icebergs. The proposed ACF-FRCNN method gave a better performance in terms of loss (18.32%), accuracy (96.34%), recall (98.32%), precision (95.97%), and the F1 score (97.13%). Compared to other conventional methods, the combined effect of ACF and FRCNN increased the speed and quality of the detection of ships and icebergs. Thus, the ACF-FRCNN method is considered a novel method for over 75 × 75 resolution ship and iceberg SAR images. Full article

Respirator use has been shown to be associated with overall discomfort. Activated carbon fiber (ACF) has potential as an alternative adsorbent for developing thinner, lightweight, and efficient respirators due to its larger surface area, microporosity, and fabric form. The purpose of this pilot study was to determine the adsorption characteristics of commercially available ACF in respirator cartridges with varying ACF composition for toluene protection. Seven ACF types (one cloth, six felt) with varying properties were tested. Seven ACF cartridge configurations with varying ACF composition were challenged with five toluene concentrations (20–500 ppm) at constant air temperature (23 °C), relative humidity (50%), and air flow (32 LPM). Breakthrough curves were obtained using photoionization detectors. Breakthrough times (10%, 50%, and 5 ppm) and adsorption capacities were compared among ACF cartridge configurations to determine their suitable application in respiratory protection. Results showed that ACF cartridges containing the densest ACF felt types had the longest average breakthrough times (e.g., ~250–270 min to reach 5 ppm breakthrough time) and those containing ACF felt types with the highest specific surface areas had the highest average adsorption capacity (~450–470 mg/g). The ACF cartridges demonstrated breakthrough times of <1 h for 500 ppm toluene and 8–16 h for 20 ppm toluene. The ACF cartridges are more reliable for use at low ambient toluene concentrations but still have potential for use at higher concentrations for short-term protection. ACF felt forms with appropriate properties (density of ~0.07 g/cm³; specific surface area of ~2000 m²/g) have shown promising potential for the development of lighter and thinner respirators for protection against toluene. Full article

This paper presents an experimental evaluation of real-time pedestrian detection algorithms and their tuning using the proposed universal performance index. With this index, the precise choice of various parameters is possible. Moreover, we determined the best resolution of the analysis window, which is much lower than the initial window. By such means, we can speed-up the processing (i.e., reduce the classification time by 74%). There are cases in which we increased both the processing speed and the classification accuracy. We made experiments with various baseline detectors and datasets in order to confirm versatility of the proposed ideas. The analyzed classifiers are those typically applied to detection of pedestrians, namely: aggregated channel feature (ACF), deep convolutional neural network (CNN), and support vector machine (SVM). We used a suite of five precisely chosen night (and day) IR vision datasets. Full article

In this paper a method for detecting and estimating the distance of a vehicle driving in front using a single black-box camera installed in a vehicle was proposed. In order to apply the proposed method to autonomous vehicles, it was required to reduce the throughput and speed-up the processing. To do this, the proposed method decomposed the input image into multiple-resolution images for real-time processing and then extracted the aggregated channel features (ACFs). The idea was to extract only the most important features from images at different resolutions symmetrically. A method of detecting an object and a method of estimating a vehicle’s distance from a bird’s eye view through inverse perspective mapping (IPM) were applied. In the proposed method, ACFs were used to generate the AdaBoost-based vehicle detector. The ACFs were extracted from the LUV color, edge gradient, and orientation (histograms of oriented gradients) of the input image. Subsequently, by applying IPM and transforming a 2D input image into 3D by generating an image projected in three dimensions, the distance between the detected vehicle and the autonomous vehicle was detected. The proposed method was applied in a real-world road environment and showed accurate results for vehicle detection and distance estimation in real-time processing. Thus, it was showed that our method is applicable to autonomous vehicles. Full article

Finding optimal parametrizations for people detectors is a complicated task due to the large number of parameters and the high variability of application scenarios. In this paper, we propose a framework to adapt and improve any detector automatically in multi-camera scenarios where people are observed from various viewpoints. By accurately transferring detector results between camera viewpoints and by self-correlating these transferred results, the best configuration (in this paper, the detection threshold) for each detector-viewpoint pair is identified online without requiring any additional manually-labeled ground truth apart from the offline training of the detection model. Such a configuration consists of establishing the confidence detection threshold present in every people detector, which is a critical parameter affecting detection performance. The experimental results demonstrate that the proposed framework improves the performance of four different state-of-the-art detectors (DPM , ACF, faster R-CNN, and YOLO9000) whose Optimal Fixed Thresholds (OFTs) have been determined and fixed during training time using standard datasets. Full article

Object tracking in challenging videos is a hot topic in machine vision. Recently, novel training-based detectors, especially using the powerful deep learning schemes, have been proposed to detect objects in still images. However, there is still a semantic gap between the object detectors and higher level applications like object tracking in videos. This paper presents a comparative study of outstanding learning-based object detectors such as ACF, Region-Based Convolutional Neural Network (RCNN), FastRCNN, FasterRCNN and You Only Look Once (YOLO) for object tracking. We use an online and offline training method for tracking. The online tracker trains the detectors with a generated synthetic set of images from the object of interest in the first frame. Then, the detectors detect the objects of interest in the next frames. The detector is updated online by using the detected objects from the last frames of the video. The offline tracker uses the detector for object detection in still images and then a tracker based on Kalman filter associates the objects among video frames. Our research is performed on a TLD dataset which contains challenging situations for tracking. Source codes and implementation details for the trackers are published to make both the reproduction of the results reported in this paper and the re-use and further development of the trackers for other researchers. The results demonstrate that ACF and YOLO trackers show more stability than the other trackers. Full article