Harsh Munshi - Academia.edu (original) (raw)
Related Authors
EMBRAPA - Empresa Brasileira de Pesquisa Agropecuária
Uploads
Papers by Harsh Munshi
2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2018
Convolutional neural networks have proved their capability over wide areas of computer vision and... more Convolutional neural networks have proved their capability over wide areas of computer vision and has lead to superlative performance in the benchmarking tasks. Efforts to train and run deep neural networks is computationally expensive and requires a cloud infrastructure equiped with appropriate hardware. In this paper, we introduce the technical details and results from our cloud service for image analysis. It includes a ConvNet over region proposals, and is able to cater the requests from a wide range of object classification and detection tasks. Our approach also encompasses an auto-scaling system to handle intensive inquiries in a short amount of time and automatically sorts the queries based on their importance. The experimental results prove that our system could offer the state-of-the-art accuracy on users’ data.
There are myriad occasions where human inclusions in a situation can be replaced by a robot which... more There are myriad occasions where human inclusions in a situation can be replaced by a robot which does the same task with ease and in a shorter duration of time. Earlier efforts in the field of vision based robotics have been primarily manual and static in nature: process being monitored at a single fixed point. Recent evolutions have led us to gesture controlled robotics which may be fascinating but manual in nature. Systems are being developed which have on-board vision: Autonomous systems that can act on the same situations at different locations. To facilitate one possible feasible solution, we have implemented a system through which an area is scanned for a particular object by a surveillance robot. Through this method autonomous monitoring of hazardous elements is made possible with a wireless camera on-board and robot monitoring various locations in a given region. The command signals are generated from the scanning through Image Processing. These signals are then passed to t...
There are myriad occasions where human inclusions in a situation can be replaced by a robot which... more There are myriad occasions where human inclusions in a situation can be replaced by a robot which does the same task with ease and in a shorter duration of time. Earlier efforts in the field of vision based robotics have been primarily manual and static in nature: process being monitored at a single fixed point. Recent evolutions have led us to gesture controlled robotics which may be fascinating but manual in nature. Systems are being developed which have on-board vision: Autonomous systems that can act on the same situations at different locations. To facilitate one possible feasible solution, we have implemented a system through which an area is scanned for a particular object by a surveillance robot. Through this method autonomous monitoring of hazardous elements is made possible with a wireless camera on-board and robot monitoring various locations in a given region. The command signals are generated from the scanning through Image Processing. These signals are then passed to t...
There are myriad occasions where human inclusions in a situation can be replaced by a robot which... more There are myriad occasions where human inclusions in a situation can be replaced by a robot which does the same task with ease and in a shorter duration of time. Earlier efforts in the field of vision based robotics have been primarily manual and static in nature: process being monitored at a single fixed point. Recent evolutions have led us to gesture controlled robotics which may be fascinating but manual in nature. Systems are being developed which have on-board vision: Autonomous systems that can act on the same situations at different locations. To facilitate one possible feasible solution, we have implemented a system through which an area is scanned for a particular object by a surveillance robot. Through this method autonomous monitoring of hazardous elements is made possible with a wireless camera on-board and robot monitoring various locations in a given region. The command signals are generated from the scanning through Image Processing. These signals are then passed to the robot to navigate it to the required position pick the object and place it to the required position using an electro-pneumatic gripping mechanism.
2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2018
Convolutional neural networks have proved their capability over wide areas of computer vision and... more Convolutional neural networks have proved their capability over wide areas of computer vision and has lead to superlative performance in the benchmarking tasks. Efforts to train and run deep neural networks is computationally expensive and requires a cloud infrastructure equiped with appropriate hardware. In this paper, we introduce the technical details and results from our cloud service for image analysis. It includes a ConvNet over region proposals, and is able to cater the requests from a wide range of object classification and detection tasks. Our approach also encompasses an auto-scaling system to handle intensive inquiries in a short amount of time and automatically sorts the queries based on their importance. The experimental results prove that our system could offer the state-of-the-art accuracy on users’ data.
There are myriad occasions where human inclusions in a situation can be replaced by a robot which... more There are myriad occasions where human inclusions in a situation can be replaced by a robot which does the same task with ease and in a shorter duration of time. Earlier efforts in the field of vision based robotics have been primarily manual and static in nature: process being monitored at a single fixed point. Recent evolutions have led us to gesture controlled robotics which may be fascinating but manual in nature. Systems are being developed which have on-board vision: Autonomous systems that can act on the same situations at different locations. To facilitate one possible feasible solution, we have implemented a system through which an area is scanned for a particular object by a surveillance robot. Through this method autonomous monitoring of hazardous elements is made possible with a wireless camera on-board and robot monitoring various locations in a given region. The command signals are generated from the scanning through Image Processing. These signals are then passed to t...
There are myriad occasions where human inclusions in a situation can be replaced by a robot which... more There are myriad occasions where human inclusions in a situation can be replaced by a robot which does the same task with ease and in a shorter duration of time. Earlier efforts in the field of vision based robotics have been primarily manual and static in nature: process being monitored at a single fixed point. Recent evolutions have led us to gesture controlled robotics which may be fascinating but manual in nature. Systems are being developed which have on-board vision: Autonomous systems that can act on the same situations at different locations. To facilitate one possible feasible solution, we have implemented a system through which an area is scanned for a particular object by a surveillance robot. Through this method autonomous monitoring of hazardous elements is made possible with a wireless camera on-board and robot monitoring various locations in a given region. The command signals are generated from the scanning through Image Processing. These signals are then passed to t...
There are myriad occasions where human inclusions in a situation can be replaced by a robot which... more There are myriad occasions where human inclusions in a situation can be replaced by a robot which does the same task with ease and in a shorter duration of time. Earlier efforts in the field of vision based robotics have been primarily manual and static in nature: process being monitored at a single fixed point. Recent evolutions have led us to gesture controlled robotics which may be fascinating but manual in nature. Systems are being developed which have on-board vision: Autonomous systems that can act on the same situations at different locations. To facilitate one possible feasible solution, we have implemented a system through which an area is scanned for a particular object by a surveillance robot. Through this method autonomous monitoring of hazardous elements is made possible with a wireless camera on-board and robot monitoring various locations in a given region. The command signals are generated from the scanning through Image Processing. These signals are then passed to the robot to navigate it to the required position pick the object and place it to the required position using an electro-pneumatic gripping mechanism.