B.H. Pansambal | SPPU University, Pune, India (original) (raw)

Papers by B.H. Pansambal

Research paper thumbnail of Human Emotion Recognition Using Gabor Variance Features with Back Propagation Neural Network Classifier

2022 IEEE Pune Section International Conference (PuneCon)

Research paper thumbnail of Raindrop Detection : Performance analysis of recent approaches for the use in electronic driver assistance systems

Advanced driver assistive system (ADAS) forms one of the most important as well as a common featu... more Advanced driver assistive system (ADAS) forms one of the most important as well as a common feature in today’s automotive industry. ADAS depends upon various sensors that aid the driver in visual or auditory feedback. Video based driver assistive systems are designed to work in clear weather and often fail to be of any help in rainy climatic conditions. This affects the overall performance of ADAS. Various research studies make use of algorithms and photometric models of raindrop for its detection and provide a reliable feedback signal. This paper reviews various techniques and photometric models defined for raindrop detection in various climatic conditions.

Research paper thumbnail of Comparative Analysis of Different Deblurring Techniques

International journal of engineering research and technology, 2018

Cameras shake during exposure time results in unpleasant image blur and is reason of rejection of... more Cameras shake during exposure time results in unpleasant image blur and is reason of rejection of many photographs. Typical blind deconvolution methods assume frequency-domain constraints on images, or extremely basic parametric forms for the motion trail during camera shake. Actual camera motion trajectory can follow convoluted path, and a spatial domain prior can preserve prominent image characteristics. A blurred image can be recognized as a convolution function of a sharp image and a blur kernel or PSF. So in order to recover the sharp image we need to split the image into its blur kernel and sharp image. The problem lies with the blur kernel estimation. Few methods assume a uniform camera blur over the image and negligible in-plane camera rotation. This unknown blur kernel estimation is called as the Blind deconvolution. Most of the deblurring techniques make use of these concepts. Few months uses sensors to calculate this blur Kernel. Paper aims reviewing all the contemporary ...

Research paper thumbnail of Camera based Forward Collision Avoidance System

1ME Student, (E & TC) Signal processing, TSSM’s BSCOER, Pune, Maharashtra, India. 2 Professor, (E... more 1ME Student, (E & TC) Signal processing, TSSM’s BSCOER, Pune, Maharashtra, India. 2 Professor, (E & TC) Signal processing, TSSM’s BSCOER, Pune, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------Abstract Car accidents and fatalities are a measure concern in today’s world. Most of the accidents on highways are of type “front impact” which is because of un-ability of driver to identify / judge the front vehicle’s movement due to lack of attention while driving. This project aims to address this issue by recognizing risk ahead of time and provide warning to user about the risk. Till today lot of work has already happened to tackle this problem and some of the projects are even implemented in high-end vehicles like VOLVO, BMW etc. Most of these projects use stereo vision algorithms and machine learning algorithms which are extensively resource hungry. So, these algorithms need ex...

Research paper thumbnail of Human Emotion Recognition Using Gabor Variance Features with Back Propagation Neural Network Classifier

2022 IEEE Pune Section International Conference (PuneCon)

Research paper thumbnail of Raindrop Detection : Performance analysis of recent approaches for the use in electronic driver assistance systems

Advanced driver assistive system (ADAS) forms one of the most important as well as a common featu... more Advanced driver assistive system (ADAS) forms one of the most important as well as a common feature in today’s automotive industry. ADAS depends upon various sensors that aid the driver in visual or auditory feedback. Video based driver assistive systems are designed to work in clear weather and often fail to be of any help in rainy climatic conditions. This affects the overall performance of ADAS. Various research studies make use of algorithms and photometric models of raindrop for its detection and provide a reliable feedback signal. This paper reviews various techniques and photometric models defined for raindrop detection in various climatic conditions.

Research paper thumbnail of Comparative Analysis of Different Deblurring Techniques

International journal of engineering research and technology, 2018

Cameras shake during exposure time results in unpleasant image blur and is reason of rejection of... more Cameras shake during exposure time results in unpleasant image blur and is reason of rejection of many photographs. Typical blind deconvolution methods assume frequency-domain constraints on images, or extremely basic parametric forms for the motion trail during camera shake. Actual camera motion trajectory can follow convoluted path, and a spatial domain prior can preserve prominent image characteristics. A blurred image can be recognized as a convolution function of a sharp image and a blur kernel or PSF. So in order to recover the sharp image we need to split the image into its blur kernel and sharp image. The problem lies with the blur kernel estimation. Few methods assume a uniform camera blur over the image and negligible in-plane camera rotation. This unknown blur kernel estimation is called as the Blind deconvolution. Most of the deblurring techniques make use of these concepts. Few months uses sensors to calculate this blur Kernel. Paper aims reviewing all the contemporary ...

Research paper thumbnail of Camera based Forward Collision Avoidance System

1ME Student, (E & TC) Signal processing, TSSM’s BSCOER, Pune, Maharashtra, India. 2 Professor, (E... more 1ME Student, (E & TC) Signal processing, TSSM’s BSCOER, Pune, Maharashtra, India. 2 Professor, (E & TC) Signal processing, TSSM’s BSCOER, Pune, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------Abstract Car accidents and fatalities are a measure concern in today’s world. Most of the accidents on highways are of type “front impact” which is because of un-ability of driver to identify / judge the front vehicle’s movement due to lack of attention while driving. This project aims to address this issue by recognizing risk ahead of time and provide warning to user about the risk. Till today lot of work has already happened to tackle this problem and some of the projects are even implemented in high-end vehicles like VOLVO, BMW etc. Most of these projects use stereo vision algorithms and machine learning algorithms which are extensively resource hungry. So, these algorithms need ex...