As we know that accidents are increasing day by day, we can also notice that many laws and regulations are posed by government in order to avoid this accidents. Accidents can be defined as the unplanned event or the mistake that may occur resulting in injury and sometimes it also leads to death. The accidents in case of two wheelers are more compared to other vehicles. This may be avoided by wearing helmets and riding vehicles without consuming alcohol. This survey is on smart helmet for accidence avoidance and also examining various related techniques. This research also helps us to understand IOT technology which is being emerged now a days .From the literature survey we find that the method proposed using microcontroller RF transmitter and other sensors is cost effective but we find the system proposed using Raspberry pi module, Pi camera, Pressure Sensor, GPS system which uses image processing algorithms is most efficient since the image processing is included so that we can easily detect the use of helmet from the rider. Smart helmet system helps to provide safety and security to the two wheeler riders.

No abstract

No abstract

Face sketch recognition is considered as a sub-problem of face recognition. Matching composite sketches with its corresponding digital image is one of the challenging tasks. A new convolution neural network (CNN) framework for matching composite sketches with digital images is proposed in this work. The framework consists of a base CNN model that uses swish activation function in the hidden layers. Both composite sketches and digital images are trained separately in the network by providing matching pairs and mismatching pairs. The final output resulted from the network's final layer is compared with the threshold value, and then the pair is assigned to the same or different class. The proposed framework is evaluated on two datasets, and it exhibits an accuracy of 78.26% with extended-PRIP (E-PRIP) and 69.57% with composite sketches with age variations (CSA) respectively. Experimental analysis shows the improved results compared to state-of-the-art composite sketch matching systems.

Abnormal event detection is a method that identifies anomalies or irregular events in the videos. The main purpose of this paper is to detect abnormal events using various methods. Abnormal event detection method enables you to find out the abnormal events which includes anomalies, outliets, discordant observations, exceptions, aberrations, surprises and peculiarities. This paper explains comprehensive survey on different methods used for abnormal event detection in different scenarios and ultimately comparitive study on different methods are discussed.