Rohit Thakur - Academia.edu (original) (raw)
Uploads
Papers by Rohit Thakur
2020 International Conference for Emerging Technology (INCET), 2020
Object detection in satellite imagery is very important for a wide array of applications in surve... more Object detection in satellite imagery is very important for a wide array of applications in surveillance system, monitoring tasks etc. The satellite images have lower resolution as compared to aerial images and hence detecting smaller objects such as vehicles, aircrafts in a remotely sensed image is a challenging task. In this paper, we focus on the comparative study of three different models namely YoloV3, SSD and RCNN. We have tested all the three models to find out which model performed best for the task of airplane detection when trained on aerial images and tested for small object detection (airplanes in our case) on satellite images. Finally, we illustrated the comparison of the three models on the basis of accuracy, losses etc.
Remote Sensing Technologies and Applications in Urban Environments V, 2020
Urban land use classes of complex nature are marked by the presence of multiple land covers and/o... more Urban land use classes of complex nature are marked by the presence of multiple land covers and/or objects in the specific spatial order. The spatial configuration of the constituent parts of the land use class is generally unique. To the extent that the specific spatial configuration is defining characteristic of a given land use class. These characteristics can be effectively leveraged to identify the land use class. In this research, we exploit the unique spatial structure of the constituent parts for the land use class for its detection. We use capsule network (CapsuleNet) for detecting some of the urban land use classes such as parking lot and golf courses. CapsuleNets use a group of neurons (called capsules) in a convolutional layer to detect a specific image primitive. Each subsequent layer detects higher order primitives, and its relationship with the lower level primitives. Thus, multiple such layers build a hierarchy of parts to learn the whole object, in this case the land use class. We conducted multiple experiments for detecting parking lots and golf courses in a collection of urban images. We used NWPU-RESISC45 dataset for conducting our experiments. Furthermore, we compared the results of CapsuleNet based architecture with standard architecture such as VGG16, which do not consider the spatial structure of the features. Our initial experiments suggest improvement in accuracy in classification of the land use classes such as parking lot and golf courses.
2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2021
Deep convolutional neural networks learn the spatial image features automatically, for classifyin... more Deep convolutional neural networks learn the spatial image features automatically, for classifying a hyperspectral image. Learning the spectral features automatically is equally important in analyzing the hyperspectral image. However, most of the earlier work treat a hyperspectral pixel as a n dimensional vector (n = no. of bands) and a separate convolution is performed over the depth. The features so learned are stacked together with the spatial features and are used for further processing. The semantics of the learned spectral features are completely ignored and are not interpretable in these approaches. We propose a simple transformation of the hyperspectral pixel to two-dimensional spectral graph (shape) and then the convolution over the same. This results in learning the spectral features that can be interpreted using spectroscopic knowledge of the material. We compared our approach with some of the common deep learning approaches for the hyperspectral data. The improvements are evident from the experiments.
2020 International Conference for Emerging Technology (INCET), 2020
Object detection in satellite imagery is very important for a wide array of applications in surve... more Object detection in satellite imagery is very important for a wide array of applications in surveillance system, monitoring tasks etc. The satellite images have lower resolution as compared to aerial images and hence detecting smaller objects such as vehicles, aircrafts in a remotely sensed image is a challenging task. In this paper, we focus on the comparative study of three different models namely YoloV3, SSD and RCNN. We have tested all the three models to find out which model performed best for the task of airplane detection when trained on aerial images and tested for small object detection (airplanes in our case) on satellite images. Finally, we illustrated the comparison of the three models on the basis of accuracy, losses etc.
Remote Sensing Technologies and Applications in Urban Environments V, 2020
Urban land use classes of complex nature are marked by the presence of multiple land covers and/o... more Urban land use classes of complex nature are marked by the presence of multiple land covers and/or objects in the specific spatial order. The spatial configuration of the constituent parts of the land use class is generally unique. To the extent that the specific spatial configuration is defining characteristic of a given land use class. These characteristics can be effectively leveraged to identify the land use class. In this research, we exploit the unique spatial structure of the constituent parts for the land use class for its detection. We use capsule network (CapsuleNet) for detecting some of the urban land use classes such as parking lot and golf courses. CapsuleNets use a group of neurons (called capsules) in a convolutional layer to detect a specific image primitive. Each subsequent layer detects higher order primitives, and its relationship with the lower level primitives. Thus, multiple such layers build a hierarchy of parts to learn the whole object, in this case the land use class. We conducted multiple experiments for detecting parking lots and golf courses in a collection of urban images. We used NWPU-RESISC45 dataset for conducting our experiments. Furthermore, we compared the results of CapsuleNet based architecture with standard architecture such as VGG16, which do not consider the spatial structure of the features. Our initial experiments suggest improvement in accuracy in classification of the land use classes such as parking lot and golf courses.
2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2021
Deep convolutional neural networks learn the spatial image features automatically, for classifyin... more Deep convolutional neural networks learn the spatial image features automatically, for classifying a hyperspectral image. Learning the spectral features automatically is equally important in analyzing the hyperspectral image. However, most of the earlier work treat a hyperspectral pixel as a n dimensional vector (n = no. of bands) and a separate convolution is performed over the depth. The features so learned are stacked together with the spatial features and are used for further processing. The semantics of the learned spectral features are completely ignored and are not interpretable in these approaches. We propose a simple transformation of the hyperspectral pixel to two-dimensional spectral graph (shape) and then the convolution over the same. This results in learning the spectral features that can be interpreted using spectroscopic knowledge of the material. We compared our approach with some of the common deep learning approaches for the hyperspectral data. The improvements are evident from the experiments.