International Journal of Trend in Scientific Research and Development · 2019 · 34 citations · 0 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionMachine LearningDeep LearningObject DetectionObject RecognitionPattern RecognitionRepresentation LearningVehicle PerceptionDeep Learning DetectionHigh PerformanceObject Detection In Autonomous DrivingReal-time Object Detection
The goal of the project is to run an object detection algorithm on every frame of a video, thus allowing the algorithm to detect all the objects in it, including but not limited to: people, vehicles, animals etc. Object recognition and detection play a crucial role in computer vision and automated driving systems. We aim to design a system that does not compromise on performance or accuracy and provides real-time solutions. With the importance of computer vision growing with each passing day, models that deliver high-performance results are all the more dominant. Exponential growth in computing power as-well-as growing popularity in deep learning led to a stark increase in high-performance algorithms that solve real-world problems. Our model can be taken a step further, allowing the user the flexibility to detect only the objects that are needed at the moment despite being trained on a larger dataset.