Dhiraj

Ashlesha Kumar, Kuldip Singh Sangwan, Dhiraj

As the proportion of road accidents increases each year, driver distraction continues to be an important risk component in road traffic injuries and deaths. The distractions caused by the increasing use of mobile phones and other wireless devices pose a potential risk to road safety. Our current study aims to aid the already existing techniques in driver posture recognition by improving the performance in the driver distraction classification problem. We present an approach using a genetic algorithm-based ensemble of six independent deep neural architectures, namely, AlexNet, VGG-16, EfficientNet B0, Vanilla CNN, Modified DenseNet, and InceptionV3 + BiLSTM. We test it on two comprehensive datasets, the AUC Distracted Driver Dataset, on which our technique achieves an accuracy of 96.37%, surpassing the previously obtained 95.98%, and on the State Farm Driver Distraction Dataset, on which we attain an accuracy of 99.75%. The 6-Model Ensemble gave an inference time of 0.024 seconds as measured on our machine with Ubuntu 20.04(64-bit) and GPU as GeForce GTX 1080.

J. L. Raheja, Dhiraj, D. Gopinath et al.

In the old age, few people need special care if they are suffering from specific diseases as they can get stroke while they are in normal life routine. Also patients of any age, who are not able to walk, need to be taken care of personally but for this, either they have to be in hospital or someone like nurse should be with them for better care. This is costly in terms of money and man power. A person is needed for 24x7 care of these people. To help in this aspect we purposes a vision based system which will take input from the patient and will provide information to the specified person, who is currently may not in the patient room. This will reduce the need of man power, also a continuous monitoring would not be needed. The system is using MS Kinect for gesture detection for better accuracy and this system can be installed at home or hospital easily. The system provides GUI for simple usage and gives visual and audio feedback to user. This system work on natural hand interaction and need no training before using and also no need to wear any glove or color strip.