1 Pedestrians and cyclists are vulnerable road users and despite their limited presence in traffic events, these 2 two groups have the most collisions resulting in injuries and fatalities. Due to problems regarding data 3 collection for pedestrians and cyclists, there is a shortcoming in the field of road safety with regards to the 4 availability and quality of data for non-motorized modes. Als...

Recently, obstacles detection and identification task in ADAS is a well-established research field. Histogram of oriented gradients (HOG) is one of the most effective obstacle feature extraction approaches to the study. In this paper, an optimization detection system based on a customized HOG descriptor is presented and investigated to achieve an accurate vehicle recognition system. The key con...

Biometrics are used for authentication. It isused to recognize a person based on their unique characteristics. Among several biometrics, Fingerprint is the most widely used and acceptable biometrics. Biometric system has several advantages over traditional methods. But it can be affected by several attacks. In this paper type 1 attack is discussed which is performed at the sensor level. Differe...

In this paper, we report on experiments with the use of local measures for depth motion for visual action recognition from MPEG encoded RGBD video sequences. We show that such measures can be combined with local space-time video descriptors for appearance to provide a computationally efficient method for recognition of actions. Fisher vectors are used for encoding and concatenating a depth desc...

Content based image retrieval is the technique to retrieve similar images from a database that are visually similar to a given query image. It is an active and emerging research field in computer vision. In our proposed system, the Interest points based Histogram of Oriented Gradients (HOG) feature descriptor is used to retrieve the relevant images from the database. The dimensionality of the H...

Nowadays, Multimodal biometrics has created a substantial interest in the field of identification management due to higher recognition performance. This paper presents a comparative analysis of different fusion levels like feature level, score level and decision level in multimodal biometrics using fingerprint and face. Histogram of Oriented Gradients (HOG) descriptor has been used for fingerpr...

The paper presents an original approach for pedestrian detection using the neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author; it represents a winner-takes-all collection of neural modules. The algorithm has the following stages: (a) feature selection using one of the three candidate techniques Histogram of Oriented Gradients (HOG)/1D ...

The paper presents an original approach for pedestrian detection in thermal imagery using Histogram of Oriented Gradients (HOG) for feature extraction and the neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author. The proposed algorithm has the following main stages: (a) detection of the regions of interest (ROI); (b) feature selection us...