MultidimensionalMultidimensional object recognition plays a very major role in the field of computer visionComputer vision. The research work in the field of self-driving cars, robotics, video surveillance system requires object detectionObject detection, localization and classification. Due to the remarkable advancement in the field of neural network, visual recognition system has achieved significant performance. In this work, RCNNRCNN and YOLOYOLO models are used to face the challenges during multidimensionalMultidimensional object detectionObject detection and classification in real time. The major goal of this work is to recognize the real-time objects using deep learningDeep learning models to help visually impaired people to make them independent and sign language detection for vocally/hearing impaired people. This work will be extended to object detectionObject detection in video also.