Anil Balaji Gonde
Research Subjects
Anil Balaji Gonde has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Akshay Dudhane
Mohammed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE
1 shared publication - Prashant W. Patil
Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology Guwahati, Guwahati, India
1 shared publication - Rudra Prakash Maheshwari
Raj Kumar Goel Institute of Technology , 5 Km Stone, Delhi-Meerut Road, Opp. Jain Tube Co. Ltd., Ghaziabad, Uttar Pradesh 201001 Ghaziabad , India
1 shared publication - Subrahmanyam Murala
Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada
1 shared publication - Subrahmanyam Murala
Trinity College Dublin
1 shared publication
Latest Publications
- 12 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 28 (10709908) , 489-493
Deep Adversarial Network for Scene Independent Moving Object Segmentation
The current prevailing algorithms highly depend on additional pre-trained modules trained for other applications or complicated training procedures or neglect the inter-frame spatio-temporal structural dependencies. Also, the generalized effect of existing works with completely unseen data is difficult to identify. Specifically, the outdoor videos suffer from adverse atmospheric conditions like poor visibility, inclement weather, etc. In this paper, a novel end-to-end multi-scale temporal edge aggregation (MTPA) network is proposed with adversarial learning for scene dependent and independent object segmentation. The MTPA is proposed to extract the comprehensive spatiotemporal features from the current and reference frame. These MTPA features are used to guide the respective decoder through skip connections. To get authentic and consistent foreground object(s), the respective scale feedback of previous frame output is provided with respective MTPA features at each decoder input. The performance analysis of the proposed method is verified on CDnet-2014 [1] and LASIESTA [2] video datasets. The proposed method outperforms the existing state-of-the-art methods with scene dependent and independent analysis.
- 12 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 28 (10709908) , 489-493
Deep Adversarial Network for Scene Independent Moving Object Segmentation
The current prevailing algorithms highly depend on additional pre-trained modules trained for other applications or complicated training procedures or neglect the inter-frame spatio-temporal structural dependencies. Also, the generalized effect of existing works with completely unseen data is difficult to identify. Specifically, the outdoor videos suffer from adverse atmospheric conditions like poor visibility, inclement weather, etc. In this paper, a novel end-to-end multi-scale temporal edge aggregation (MTPA) network is proposed with adversarial learning for scene dependent and independent object segmentation. The MTPA is proposed to extract the comprehensive spatiotemporal features from the current and reference frame. These MTPA features are used to guide the respective decoder through skip connections. To get authentic and consistent foreground object(s), the respective scale feedback of previous frame output is provided with respective MTPA features at each decoder input. The performance analysis of the proposed method is verified on CDnet-2014 [1] and LASIESTA [2] video datasets. The proposed method outperforms the existing state-of-the-art methods with scene dependent and independent analysis.
- 1 March 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1411-1416
Color and Texture Features for Image Indexing and Retrieval
The novel approach combines color and texture features for content based image retrieval (CBIR). The color and texture features are obtained by computing the mean and standard deviation on each color band of image and sub-band of different wavelets. The standard Wavelet and Gabor wavelet transforms are used for decomposing the image into sub-bands. The retrieval results obtained by applying color histogram (CH) + Gabor wavelet transform(GWT) to a 1000 image database demonstrated significant improvement in precision and recall, compared to the color histogram (CH), wavelet transform (WT), wavelet transform + color histogram (WT + CH) and Gabor wavelet transform (GWT).
- 1 March 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1411-1416
Color and Texture Features for Image Indexing and Retrieval
The novel approach combines color and texture features for content based image retrieval (CBIR). The color and texture features are obtained by computing the mean and standard deviation on each color band of image and sub-band of different wavelets. The standard Wavelet and Gabor wavelet transforms are used for decomposing the image into sub-bands. The retrieval results obtained by applying color histogram (CH) + Gabor wavelet transform(GWT) to a 1000 image database demonstrated significant improvement in precision and recall, compared to the color histogram (CH), wavelet transform (WT), wavelet transform + color histogram (WT + CH) and Gabor wavelet transform (GWT).