Browse applications built on YOLO YOLOv7 technology. Explore PoC and MVP applications created by our community and discover innovative use cases for YOLO YOLOv7 technology.
-License plate recognition is an important technology with many applications like electronic toll collection, traffic law enforcement, and vehicle tracking and identification. The goal of an LPR system is to automatically detect and extract the license plate number from an image or video of a car -License plate detection. YOLOv8 can be trained on a dataset of car images with labeled license plates to build a detection model. At runtime, it will take an input image, run the model, and return the coordinates of any license plates it finds -The license plate image can be extracted from the original image using the coordinates identified by YOLOv8. OpenCV functions like cropping and perspective transforms can prepare the license plate image for the next step -The license plate characters then need to be segmented into individual letters/digits. This involves techniques like morphological operations, contours, and character segmentation in OpenCV -Optical character recognition is used to identify each character. The segmented characters can be fed into a pretrained OCR model like Tesseract or a custom CNN model built with OpenCV and machine learning -The pipeline outputs the license plate text which can then be used for various applications. Building this system with OpenCV and YOLOv8 allows for fast, accurate, and robust license plate recognition in real-time. It has important uses in transportation, law enforcement, and security domains
In today's world, saving money has become challenging due to price inflation, previous debts, and lack of financial discipline. Our gamified mobile app addresses these challenges by offering a fun and rewarding approach to saving. Through goal-setting, SMS expense tracking, and motivational messages, users can develop better financial habits and achieve their savings targets. Join us in overcoming these obstacles and achieving long-term financial success! Through goal-setting, SMS expense tracking, and motivational messages, users can develop better financial habits and achieve their savings targets. Join us in overcoming these obstacles and achieving long-term financial success!
Project description: The project idea is to automate the process of determining who is responsible for a car accident in order to reduce traffic congestion. Using computer vision, we analyze the pictures and determine if there is any damage and how deep it is. We determine the vehicle's position, and use a fault recognition decision-making system powered by GPS data and text lexical analysis algorithm , to determine which vehicle is responsible for the accident, as well as the mistake percentage of each vehicle. Resulting in a much easier and automatic way to clear the roads in cases of traffic jams and more reliable solution for the users to a better optimization of their time.
ARA utilizes artificial intelligence and computer vision technologies to examine surveillance footage from store cameras, providing businesses with valuable insights into both customer behavior and staff performance. In addition to generating analytics, the software goes a step further by recommending operational enhancements. This includes optimizing store layouts to improve customer experience and facilitating informed decision-making. By seamlessly integrating data-driven suggestions, ARA proves to be a valuable tool that positively impacts both the profitability of businesses and the overall quality of customer service within the retail sector.
Problem Statement: In the Kingdom of Saudi Arabia, the lack of accessibility to technologies for people with disabilities is a growing problem due to the lack of technologies that understand their hand gestures, lip reading, or voice commands in Arabic. Most technologies only rely on text-based inputs, which makes it difficult for people with disabilities to use them. Solution: Our solution "Nabaa" or " نبأ " which is an arabic name means "News that Has Great Importance". Nabaa is a groundbreaking AI-powered tool that empowers people with disabilities to live more independent and fulfilling lives. Nabaa's AI model can understand and interpret sign language and gestures, allowing users to interact with digital devices and services in a way that is natural and intuitive.
Our AI-based product will be a comprehensive platform that utilizes computer vision and sensor technology for sports to detect and analyze all game events, calculate advanced statistics and analytics, and provide Generative AI actionable insights to optimize tactics.All sports will have three levels (professionals - amateurs - beginners), and at a later stage, the portal will be a unique platform for players to avoid mistakes in the game that lead to physical consequences so that injuries are prevented.General points:Starting with tennis, then football and Formula 1 racing.A gradual membership with various packages to purchase is available to suit all sports levels and different financial capabilities using different types of cameras.Family, friends, and coaches can take videos of players and then feed them into the system to be analyzed. There is a guide for videos and recommendations for all types of cameras.
In construction projects, safety is non-negotiable but often challenging to maintain. Traditional methods fall short of effectively monitoring widespread sites, resulting in increased risk and safety protocol violations. Safetyify addresses these challenges head-on by incorporating AI-driven monitoring solutions tailored to construction environments. Our system uses advanced computer vision algorithms to identify and monitor workers in real time. Safetyify can detect PPE compliance, workers breaching unsafe zones, and ensure a safe distance from heavy machinery is maintained. For instance, an immediate alert is sent to the site manager if a worker is found without a helmet or is detected under a suspended load. But Safetyify goes beyond immediate alerts. It collects data that can be used for future safety audits, and training, and to refine current safety protocols. This wealth of data serves as a repository for continuous improvement, helping to build an increasingly safer work environment over time. Overall, Safetyify serves as a guardian of construction site safety, harnessing the power of artificial intelligence to enforce safety protocols, prevent accidents, and inform future safety initiatives.
Our innovative startup is transforming the way car owners and insurance companies in Saudi Arabia navigate the complexities of vehicle repair and maintenance. With a user-friendly mobile app at its core, our solution combines the power of generative AI for damage assessment with the convenience of a repair chatbot and a sophisticated recommendation system for trusted repair shops. By seamlessly integrating these cutting-edge technologies, we're simplifying the process of car damage estimation, connecting users with reliable repair facilities, and enabling insurance companies to streamline claims processing. Our commitment to leveraging generative AI ensures accurate and efficient services in a rapidly evolving market, making car repair and maintenance hassle-free for everyone, including insurance companies seeking faster and more precise assessments.
Advancing Medical Diagnostics: Bone Fracture Detection Using X-rays In the realm of medical imaging, the utilization of X-rays for diagnosing bone fractures has been an invaluable tool that has revolutionized the field of orthopedics. Bone fractures are a common yet critical medical issue, and their accurate and timely detection is crucial for effective treatment and patient care. Bone fracture detection using X-ray datasets is a remarkable application of artificial intelligence (AI) that has the potential to revolutionize medical diagnosis and treatment planning. This technology leverages the power of machine learning algorithms to assist radiologists and medical professionals in accurately identifying and classifying fractures in X-ray images. It offers several benefits, including improved accuracy, faster diagnosis, and reduced human error. The ongoing research and development in this field aim to enhance the accuracy, efficiency, and accessibility of bone fracture detection using X-rays. Advancements in imaging technology, artificial intelligence, and telemedicine are poised to further improve fracture diagnosis, especially in remote or underserved areas where access to specialized medical care is limited. As these innovations continue to evolve, the medical community moves closer to more effective, precise, and timely detection of bone fractures, ultimately improving patient outcomes and quality of care.
Smart E-health system for patient relations based on artificial intelligence Our team idea is about creating a health environment that helps patients and improve there experience with E-health system. with using the artificial intelligence on the website that we named it “sela”. Which means “link” or “connect “ in Arabic. We choose this idea because we want to provide a better level of services and reduce the burden on patient relations staff in a way that may achieve 2030 Vision by activating and using artificial intelligence in the health field. The AI type that we used is a bot that identifies patient complaints , inquiries, and ensures that it is communicated to the concerned authorities. Our website has a property that supports people with difficulty as deaf by using the camera which understands sign language to answer them .
Lowering Medical Expenses: Diagnose helps to reduce healthcare costs by speeding up diagnoses and improving health outcomes. Early detection of disease through our AI models enables more targeted and cost-effective interventions, potentially preventing costly complications or long-term treatment. Sharing Effort: Diagnose enables healthcare professionals to leverage our AI models to create a seamless integration of technology and human knowledge. By bringing radiologists, clinicians and other providers together to provide the highest quality of care, our technology serves as a reliable partner. By working together, we open up new possibilities in diagnostics and ensure the best possible results for patients. Quicker Detection: Diagnose AI models facilitate a significantly faster diagnostic process. Our models quickly analyze medical images, resulting in instantaneous results that allow healthcare professionals to make informed decisions quickly. Peerless Accuracy: Through rigorous training on extensive and varied datasets of high quality, our models have acquired the ability to identify even the most nuanced patterns and anomalies.
In our project, we aim to address the problem of unsafe overtaking of large trucks by using a computer vision solution based on a YOLOV8 model trained on the CoCo dataset for detecting objects. To detect trucks accurately on the road, a bounding box annotation is implemented using the CV2 library and supervision library. The system uses: - A camera on large trucks. - The YOLOv8 object detection model. - The COCO dataset. - Direction detection algorithm . - Supervision library for computer vision functions. The accuracy of the model was tested by creating a demo scenario and running it on Google Colab. Because Colab does not support video playback, an output video was rendered and saved to a shared Google Drive folder for team members to view. The system detects nearby vehicles and objects and measures distances to objects ahead. It also outputs an LED display for vehicles behind the truck: - The green light means: safe to overtake. - The red light means: unsafe, stay behind the truck. Using this solution, drivers can safely overtake trucks by detecting the presence and location of trucks on the road. This could reduce the number of traffic accidents and reduce road congestion caused by unsafe overtaking practices.
If we think a new model has important public safety or security implications, we add it to the tracker. New entries usually introduce a capability that hadn’t previously existed, or represent the proliferation of a flagged capability of concern. Therefore, it is necessary and important for the facilities to have a tracking device to ensure the safety of the members of this facility, including employees and visitors. We will develop it to counting time lapse for employees for example how long they took time on lunch break or how long he was out of the facility . We have built a model that contributes to identifying the risks that a person possesses, and they are identified and identified, and after that, an alert is made about the presence of a surrounding danger . Also this model it will make us tracking footsteps of the people and the places they went .
Application that helps all age groups to detect eye diseases early by AI Technologies and annually screening from home ,increase knowledge by ChatGPT ,filtering patients with ophthalmologists and hospital appointments . According to researches there are millions cases with eye problems in Saudi Arabia and all of them can lead to BLINDNESS Our Application will helps these cases and diagnose it before it grows. Value of Ebsar: Early diagnosis By AI algorithms, before it grows, Telemedicine, Teleconsultation prematches via Ebsar’s AI, Using ChatGPT To increase patient’s knowledge, More Scalability, Saving time for patients and hospitals by apply check up access from home,
CogniClass project aims to address the challenges faced in classroom engagement and evaluation by establishing a user-friendly and Ministry of Education-approved platform. The platform will have the following features: - Student activity monitoring: the platform will record student movements and interactions within the classroom, providing valuable insights into their engagement levels. - Data analysis and reporting: analyzing the collected data, the platform will generate monthly reports that highlight each student’s academic progress, identify weaknesses, and offer specific suggestions for improvement. - Improved parent-teacher communication: the generated reports will be shared with parents, fostering effective communication between teachers and parents regarding the student’s educational status. This will enable proactive intervention and collaboration towards the student’s development. - Examination behavior monitoring: the platform will also monitor students’ behavior during exams, accurately identifying any violations or misconduct. The administration will be promptly notified, providing them with the necessary information to take appropriate actions. The project’s AI models are: - Face recognition and tracking model. - Activity analysis model. - The recommendation system.
In this project, we will employ computer vision in the field of object detection and facial recognition, to reduce the problem of littering in parks and public places by developing a system to identify people who throw waste in public places. Such that, if the person throw a trash, the system will detect the trash that the person holds, then the system will calculate the distance between the trash(object) and the hand, if that distance goes over a specific distance, the violation will be recorded. And the system will record his face and compare it to the database, then getting his government ID and issuing a digital violation to him directly. Also, there will be a dashboard for the admins to see how many volitions has been recorded and general information's about it.