scispace - formally typeset
Search or ask a question

Answers from top 17 papers

More filters
Papers (17)Insight
Experiments show that the proposed framework can detect objects and figure out their position accurately.
Both the simulation and experimental results indicate that the proposed method can effectively detect the presence and location of foreign objects.
The results confirm that the method enables the manipulator system to detect objects without precise control.
Open accessProceedings ArticleDOI
01 Sep 2017
14 Citations
In such cases, even given a decent background model, it is not trivial to detect foreground objects.
Thus ultrasound sensor seems to be a good solution to detect and recognize several objects.
The experimental results show that the proposed method can correctly identify real moving objects from frame to frame and can effectively detect small-sized objects and objects with small motion vectors and residues, as well as by recognizing moving objects even under occlusion.
The experimental results demonstrate that our method can quickly and accurately detect moving objects in dynamic scenes.
Proceedings ArticleDOI
10 Jul 1999
The method can also detect people in static imagery.
Experimental results show that the method proposed in this paper can detect moving objects exactly and effectively.
Experimental results demonstrate the effectiveness of the proposed method to detect and track objects in real video sequences.
Experiments verify that the algorithm is able to detect the size, position and orientation of general objects rapidly and precisely.
Experimentation on various videos promises that the proposed method can detect foreground objects from the frames of moving camera with negligible falsealarms.
Our experimental results indicate that our method can successfully detect the intended human objects.
This paper presents an effective method to detect moving objects for videos captured by a moving camera.
Thus by processing of the video frames, different objects will detect.
It is shown in the experiments that the proposed method can detect moving objects successfully in such cases.
In this paper, we propose a new approach that can detect the foreground objects with frequent and/or infrequent motions.

Related Questions

What is object detection?5 answersObject detection is a computer vision technique that involves identifying and locating specific objects within images or videos. Unlike simple object classification, object detection not only determines if an object belongs to a particular class but also pinpoints its position within the scene by enclosing it in a bounding box. This process is crucial for various applications such as inventory management in retail, autonomous vehicle development, surveillance systems, and more. Object detection utilizes traditional methods like Viola-Jones, SIFT, and histogram of oriented gradients, as well as modern deep learning networks such as CNN, RCNN, YOLO, and others. These algorithms enable accurate object localization, high-speed processing, and efficient identification of objects and their instances in images or videos.
What is machine vision in object detection?5 answersMachine vision in object detection refers to the use of artificial intelligence (AI) and computer vision techniques to enable machines to "see" and identify objects in images or videos. It involves the analysis and interpretation of visual data to recognize and classify objects based on their characteristics and spatial properties. Machine vision technologies, such as neural network convolutional (CNN) models, are used to extract spectral and spatial information from images, allowing for accurate classification and localization of objects. Object detection in computer vision has various applications, including object tracking, automatic driving, anomaly detection, and improving safety and productivity in industries like construction. By leveraging machine vision, companies can develop advanced systems that not only detect objects but also shape perceptions of automation and influence the future of industries.
How to detect fake news?3 answersFake news detection involves identifying reports that are intentionally false or hoaxes disseminated through mainstream news sources or social media platforms. Several studies have been conducted to detect fake news using machine learning techniques. Deep learning methods such as CNN, Bidirectional LSTM, and ResNet, combined with pre-trained word embedding, have shown promising results. Fact-checking is also important in detecting fake news. Machine learning models such as Support Vector Machine, Naive Bayes, and Neural Network have been used for fake news detection, with Support Vector Machine achieving high accuracy. Feature extraction and machine learning algorithms, including Long-Short-Term Memory, have been proposed for fake news detection, showing higher performance compared to benchmark models.
Are Stiiizys detectable in metal detectors?5 answers
How can you tell if a money detector is fake?5 answers
How to detect objects in images using Opencv?7 answers

See what other people are reading

How can an autonomous underwater vehicle track subsea cables using cameras?
5 answers
Autonomous Underwater Vehicles (AUVs) can track subsea cables using various sensors and technologies. One approach involves utilizing electromagnetic localization signals for cable tracking. Another method includes using multibeam echosounders and fluxgate magnetometers to track buried pipelines, which can also be adapted for cable tracking. Additionally, AUVs equipped with visual inspection systems can detect underwater targets, enhancing subsea exploration capabilities. Acoustical sensors like side-scan sonars and forward-looking sonars are commonly used for seabed inspection tasks, providing high-range data for target identification. These technologies, combined with advanced algorithms and neural networks, enable AUVs to autonomously track subsea cables efficiently and accurately, even in challenging underwater environments.
How to upload image here?
5 answers
To upload an image efficiently, various methods and systems can be utilized. One approach involves displaying an upload page with editing options, selecting the image, and transmitting it to a server while allowing for simultaneous editing. Another method includes defining an image area on a display screen, creating an image file, and uploading it to a website server using position data from a pointing device. Additionally, camera equipment with route setting capabilities can be employed to shoot and store images, set upload routes, and save images into a computer based on user actions and upload signals. Furthermore, an image upload processing system can simplify the process by automatically scaling uploaded images to generate target images based on pre-set resolution ratios, enhancing efficiency in image processing.
Is there a difference between pixel threshold and zooming capability in cameras used for digital photography?
4 answers
Pixel threshold and zooming capability in digital cameras are distinct features. Pixel threshold refers to the resolution comparison between generated and user-selected files, determining the final digital zoom image resolution. On the other hand, zooming capability involves processes like thinning pixel data and zooming processing based on the zooming magnification factor, with adjustments made when zooming is below or above a certain threshold value. Digital cameras often rely on digital zooming due to the lack of optical zoom in single-sensor devices, necessitating efficient computational techniques for high-quality output. Therefore, while pixel threshold governs image resolution adjustments, zooming capability focuses on the mechanisms enabling digital zoom functionality in cameras.
What are the historical and legal contexts surrounding the use of consecutive matching striations (CMS) in firearm identification?
5 answers
Consecutive Matching Striations (CMS) play a significant role in firearm identification within historical and legal contexts. The concept of CMS has been utilized as a quantitative method to describe pattern matches in forensic firearm examination. It has been crucial in determining the credibility of expert witnesses in US Courts of Law, as discussed in the Daubert trilogy. Additionally, CMS has been employed to identify striation patterns on bullets, aiding in the classification of firearms with an average accuracy rate of around 84.67% using machine learning techniques. Furthermore, the automated analysis of 3D surface measurements of bullet land impressions has enhanced the identification of matches and matchability of barrels, showcasing the practical application of CMS in forensic investigations.
How did convolutional neural networks become popular for image recognition?
4 answers
Convolutional neural networks (CNNs) gained popularity in image recognition due to their ability to efficiently process visual information. CNNs excel in extracting features from images, making them ideal for tasks like object detection and classification. The development of CNNs has seen enhancements in various components like convolutional layers, pooling layers, activation functions, and optimization techniques, leading to faster and more accurate image processing. Researchers have also explored innovative CNN architectures, such as parallel cascaded convolutional networks, to improve accuracy while considering model size and deployment convenience. The robust performance of CNNs in handling large images and their effectiveness in feature extraction have made them a cornerstone in image recognition applications, driving their widespread adoption in the field of artificial intelligence.
Why cracks are the common problem in concrete?
5 answers
Cracks in concrete structures are a common issue due to various factors such as faulty design, construction errors, overloading, and internally induced stresses. These cracks can be classified into structural and non-structural categories, with structural cracks posing safety risks to buildings. The formation of cracks in concrete can lead to reduced load-bearing capacity, compromised tightness, and aesthetic deterioration of structures. Detection of cracks is traditionally done manually, which is time-consuming and impractical for regular monitoring, leading to the development of automatic detection methods using artificial neural networks and machine learning. Despite the significant impact of cracking on construction projects, the exact financial implications are not always clear due to inadequate record-keeping, potentially resulting in hidden costs and underestimation of the true impact.
When is alaysed region area measured by winrhizo?
5 answers
The analyzed region area is measured by WinRHIZO when assessing the active area of a semiconductor sensor using the Active Region Extent Assessment with X-rays (AREA-X) method. This method utilizes a monochromatic, micro-focused X-ray beam to measure the depth of the responsive sensor volume, allowing for the study of local inhomogeneities, inefficiencies, and the overall extent and shape of the active sensor volume. In contrast, other methods like the emergency obtaining method for designated region area using DEM data and video data from an unmanned plane focus on improving the speed and accuracy of determining designated region areas during emergencies. Additionally, the region area measuring method based on a terminal infrared sensing mode enhances efficiency and accuracy in measuring region areas compared to manual methods.
What are the current state-of-the-art techniques used in digital beamforming?
4 answers
The current state-of-the-art techniques in digital beamforming involve advanced signal processing methods to enhance communication systems. These techniques include incorporating antenna arrays to steer electromagnetic waves towards desired directions, utilizing machine learning for complex beamforming problems, exploring artificial intelligence applications for optimal beamforming performance, and employing digital beamforming to improve power and spectral efficiencies in cellular and satellite services. Additionally, beamforming methods focus on adapting irradiation patterns, canceling interference, and enhancing system performance through linear processing methods. The evolution of beamforming has shifted from convex/nonconvex optimization to optimization-to-learning approaches, showcasing a diverse range of applications in radar, communications, medical imaging, and more. Researchers are addressing challenges and exploring opportunities to further enhance beamforming technologies for future advancements.
What are the most important papers by Florence Bareyre?
5 answers
Florence Bareyre's significant papers include those focusing on the seismic vulnerability assessment of modern masonry buildings in Florence, Italy. Additionally, Bareyre's works contribute to the analysis of territorial impacts of future projects in the area around Florence, starting from the province of Pistoia and extending to Florence through the Prato province. These papers shed light on the structural vulnerabilities of historical buildings in Florence and provide insights into the potential consequences of future development projects in the region. Bareyre's research plays a crucial role in understanding the architectural and seismic aspects of buildings in Florence, offering valuable information for urban planning and preservation efforts in the city.
What are the current advancements in brain tumor diagnosis, treatment, and prevention?
5 answers
Current advancements in brain tumor diagnosis, treatment, and prevention encompass various innovative approaches. Machine learning algorithms have shown enhanced efficiency in brain tumor detection, while recent developments in automated methods have improved multiclass brain tumor detection and classification. Clinical trials reflect advanced insights into cancer immunology and genomics, emphasizing the need for personalized therapies and molecular screening for rare abnormalities in brain tumors. Imaging techniques play a crucial role in diagnosing and planning treatments for brain tumors, with ongoing research focusing on targeted therapies, immunotherapy, and nanotechnological drug delivery systems. The integration of standardized image acquisition and advanced imaging technologies like 23Na MRI and CEST imaging is expected to enhance tumor perception and treatment response assessment in clinical trials.
What are the technologies for detecting crossheads and turns indoors with opencv technology?
4 answers
To detect crossheads and turns indoors using OpenCV technology, various methods have been proposed in recent research. One approach involves utilizing head detection and tracking algorithms like Haar-like features, Haar Training, and CMT. Another method introduces the Motion-aware Pseudo Siamese Network (MPSN), which leverages head motion information to guide deep models for effective head feature extraction in indoor scenarios. Additionally, a navigation system based on Visible Light Communication (VLC) using RGB LEDs and a photodetector has been developed for indoor applications, enabling spatial direction determination through optical signals. Furthermore, a real-time human head detection and tracking method using RGBD images has been proposed for fall detection systems, showcasing superior performance compared to existing methods. These technologies offer innovative solutions for accurate and efficient indoor head detection and tracking.