Ashutosh Kulkarni

Ashutosh Kulkarni

Auto-generated profile, based on publicly available information

Ashutosh Kulkarni

Computer Vision and Pattern Recognition Laboratory, Department of Electrical Engineering, Indian Institute of Technology Ropar, Rupnagar, India

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 September 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
PPPrashant W. Patil
Prashant W. Patil
ADAkshay Dudhane
Akshay Dudhane
AKAshutosh Kulkarni
Ashutosh Kulkarni
SMSubrahmanyam Murala
Subrahmanyam Murala
AGAnil Balaji Gonde
Anil Balaji Gonde
SGSunil Gupta
Sunil Gupta
Moving object segmentation (MOS) in videos received considerable attention because of its broad security-based applications like robotics, outdoor video surveillance, self-driving cars, etc. The current prevailing algorithms highly depend on additional trained modules for other applications or complicated training procedures or neglect the inter-frame spatio-temporal structural dependencies. To address these issues, a simple, robust, and effective unified recurrent edge aggregation approach is proposed for MOS, in which additional trained modules or fine-tuning on a test video frame(s) are not required. Here, a recurrent edge aggregation module (REAM) is proposed to extract effective foreground relevant features capturing spatio-temporal structural dependencies with encoder and respective decoder features connected recurrently from previous frame. These REAM features are then connected to a decoder through skip connections for comprehensive learning named as temporal information propagation . Further, the motion refinement block with multi-scale dense residual is proposed to combine the features from the optical flow encoder stream and the last REAM module for holistic feature learning. Finally, these holistic features and REAM features are given to the decoder block for segmentation. To guide the decoder block, previous frame output with respective scales is utilized. The different configurations of training-testing techniques are examined to evaluate the performance of the proposed method. Specifically, outdoor videos often suffer from constrained visibility due to different environmental conditions and other small particles in the air that scatter the light in the atmosphere. Thus, comprehensive result analysis is conducted on six benchmark video datasets with different surveillance environments. We demonstrate that the proposed method outperforms the state-of-the-art methods for MOS without any pre-trained module, fine-tuning on the test video frame(s) or complicated training.

30 November 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
AKAshutosh Kulkarni
Ashutosh Kulkarni
PPPrashant W. Patil
Prashant W. Patil
SMSubrahmanyam Murala
Subrahmanyam Murala
SGSunil Gupta
Sunil Gupta
Automated surveillance is widely opted for applications such as traffic monitoring, vehicle identification, etc . But, various weather degradation factors such as rain and snow streaks, along with atmospheric veil severely affect the perceptual quality of an image, eventually affecting the performance of these applications. There exist weather specific (rain, haze, snow, etc .) methods focusing on respective restoration task. As image restoration is a preprocessing step for high level surveillance applications, it is practically inapplicable to have different architectures for different weather restoration. In this paper, we propose a lightweight unified network, having 1.1M parameters (1 / 40 $^{th}$ and 1 / 6 $^{th}$ of the existing state-of-the-art rain with veil removal, and snow with veil removal methods respectively) for removal of rain and snow along with the veiling effect present in the images. In this network, we propose two parallel streams to handle the degradations and restoration: First, degradation removal stream (DRS) focuses mainly on removing randomly repeating degradations i.e., rain and snow streaks, through the proposed adaptive multi-scale feature sharing block (AMFSB) and stage-wise subtractive block (SSB). Second, feature corrector stream (FCS) mainly focuses on refining the partial outputs of the first stream, reducing the veiling effect and acts supplementary to the first stream. Finally, we leverage contrastive regularization for better convergence of the proposed network. Substantial experiments on synthetic as well as real-world images, along with extensive ablation studies, demonstrate that the proposed method performs competitively with the existing state-of-the-art methods for multi-weather image restoration. The code is available at: https://github.com/AshutoshKulkarni4998/UVRNet .

10 December 2021 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
AKAshutosh Kulkarni
Ashutosh Kulkarni
PPPrashant W. Patil
Prashant W. Patil
SMSubrahmanyam Murala
Subrahmanyam Murala
Presence of rainy artifacts severely degrade the overall visual quality of a video and tend to overlap with the useful information present in the video frames. This degraded video affects the effectiveness of many automated applications like traffic monitoring, surveillance, etc. As video deraining is a pre-processing step for automated applications, it is highly demanded to have a lightweight deraining module. Therefore, in this paper, a “Progressive Subtractive Recurrent Lightweight Network” is proposed for video deraining. Initially, the Multi-Kernel feature Sharing Residual Block (MKSRB) is designed to learn different sizes of rain streaks which facilitates the complete removal of rain streaks through progressive subtractions. These MKSRB features are merged with previous frame output recurrently to maintain the temporal consistency. Further, multi-receptive feature subtraction is performed through Multi-scale Multi-Receptive Difference Block (MMRDB) to avoid loss of details and extract high-frequency information. Finally, progressively learned features through MKSRB and recurrent feature merging are aggregated with fused MMRDB features which outputs the rain-free frame. Substantial experiments on prevailing synthetic datasets and real-world videos verify the superior performance of the proposed method over the existing state-of-the-art methods for video deraining.

16 February 2023
Verified
Book Chapter
Closed access
PDF file
AKAshutosh Kulkarni
Ashutosh Kulkarni
SPShruti S. Phutke
Shruti S. Phutke
SMSubrahmanyam Murala
Subrahmanyam Murala

3 October 2022 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
AKAshutosh Kulkarni
Ashutosh Kulkarni
SMSubrahmanyam Murala
Subrahmanyam Murala
Adherent raindrops, rainstreaks and snow severely degrade the perceptual quality of an image, eventually affecting the performance of several computer vision based applications which are applied in outdoor scenarios, e.g. , traffic monitoring, autonomous driving, etc . Due to the complex appearance properties, removal of such degradations from an image is a challenging task. Working towards mitigating this problem, in this paper, a lightweight network named as WiperNet is proposed which tackles the problem of raindrops, rain streaks and snow removal present in an image. The WiperNet makes use of the proposed Dual Restoration (DR) mechanism, where the input features are processed twice through the network. In the network, Multi-scale Context Aware Residual Block (MCARB) is proposed for integrating contextual information from various scales. Also, Adaptive Varying Receptive Fusion Block (AVRFB) is proposed for adaptively fusing the information acquired through different dilation rates. Finally, we propose a Feature Refinement Stream which makes use of multiple kernel sizes of convolution filters and spatio-channel attention blocks for focusing on relevant information for effective removal of the degradations while using the coarse outputs of the features from the initial layers of the network. Substantial experiments and ablation study scrutinize that the proposed lightweight WiperNet outperforms the existing state-of-the-art methods for raindrop, rain streak and snow removal. The code is provided at https://github.com/AshutoshKulkarni4998/WiperNet .

5 September 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
AKAshutosh Kulkarni
Ashutosh Kulkarni
SPShruti S. Phutke
Shruti S. Phutke
SVSantosh Kumar Vipparthi
Santosh Kumar Vipparthi
SMSubrahmanyam Murala
Subrahmanyam Murala
Visibility challenges such as atmospheric haze, water turbidity, etc. are imposed while capturing images in various mediums like aerial, outdoor, underwater, etc. Such reduction in visibility affects the functioning of high-level computer vision applications like object detection, semantic segmentation, military surveillance, earthquake assessment, etc. The existing methods either rely on incorporating additional prior information during the training process or yield less than optimal results when analysed on images with varying levels of degradation, reason being the absence of both local and global dependencies within the extracted features. This paper presents a generalized transformer based architecture for aerial, outdoor and underwater image enhancement. We propose a novel space aware deformable convolution based multi-head self attention containing spatially attentive offset extraction. Here, the deformable multi-head attention is introduced to reconstruct fine level texture in the restored image. Additionally, we introduce a spatially attentive offset extractor within the deformable convolution to prioritize relevant contextual information. Further, we propose an edge enhancing feature fusion block for restoring the edge details in the image along with learning enriched features from multi-stream information. Finally, we propose a global context aware channel attentive feature propagator having a dual functionality of global information extraction and provision of channel attention. Comprehensive experimentation conducted on both synthetic and real-world datasets, along with thorough ablation study, showcases that the proposed approach performs optimally when compared with the existing methods on aerial, outdoor, and underwater image enhancement.