Abhijit Mahalanobis

@conference{Arif2022,

title = {Background-Tolerant Object Classification with Embedded Segmentation Mask for Infrared and Color Imagery},

author = {Maliha Arif and Calvin Yong and Abhijit Mahalanobis and Nazanin Rahnavard},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Final_ICIP2022_MA_submission.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/bg_poster_ICIP2022_Single.jpg},

year  = {2022},

date = {2022-10-16},

urldate = {2022-10-16},

booktitle = {IEEE International Conference on Image Processing},

abstract = {Even though convolutional neural networks (CNNs) can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that networks often learn background textures, which are not relevant to the object of interest. In turn this makes the networks susceptible to variations and changes in the background

which may negatively affect their performance. 



We propose a new three-step training procedure called split training to reduce this bias in CNNs for object recognition using Infrared imagery and Color (RGB) data. Our split training procedure has three steps. First, a baseline model is trained to recognize objects in images without background, and the activations produced by the higher layers are observed. Next, a second network is trained using Mean Square Error (MSE)  loss to produce the same activations, but in response to the objects embedded in background. This forces the second network to ignore the  background while focusing on the object of interest. Finally, with layers producing the activations frozen, the rest of the second network is  trained using cross-entropy loss to classify the objects in images with background. Our training method outperforms the traditional training procedure in both a simple CNN architecture, as well as for deep CNNs like VGG and DenseNet, and learns to mimic human vision which focuses more on shape and structure than background with higher accuracy. 



Index Terms— infrared imagery, background invariant learning, grad-CAM, split training, MS-COCO},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Performance Evaluation of Boosted 2-stream TCRNet},

author = {Shah Hassan and MdJibanul Haque Jiban and Abhijit Mahalanobis},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/paper.pdf},

year  = {2022},

date = {2022-03-02},

urldate = {2022-03-02},

publisher = {International Congress on Information and Communication Technology},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{jiban2021icip,

title = {Two-Stream Boosted TCRNET for Range-Tolerant Infra-Red Target Detection},

author = {Md Jibanul Haque Jiban and Shah Hassan and Abhijit Mahalanobis},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Two-Stream_TCRNet__IEEE_ICIP2021.pdf},

year  = {2021},

date = {2021-09-19},

publisher = {IEEE Conference on Image Processing},

abstract = {The detection of vehicular targets in infra-red imagery is a challenging task, both due to the relatively few pixels on target and the false alarms produced by the surrounding terrain clutter. It has been previously shown [1] that a relatively simple network (known as TCRNet) can outperform conventional deep CNNs for such applications by maximizing a target to clutter ratio (TCR) metric. In this paper, we introduce a new form of the network (referred to as TCRNet-2) that further improves the performance by first processing target and clutter information in two parallel channels and then combining them to optimize the TCR metric. We also show that the overall performance can be considerably improved by boosting the performance of a primary TCRNet-2 detector, with a secondary

network that enhances discrimination between targets and clutter in the false alarm space of the primary network. We analyze the performance of the proposed networks using a publicly available data set of infra-red images of targets in natural terrain. It is shown that the TCRNet-2 and its boosted version yield considerably better performance than the original TCRNet over a wide range of distances, in both day and night conditions.



Index Terms— TCRNet, Infrared, Target Detection, MWIR, Surveillance},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ArifICIP2021,

title = {Few Shot Learning for Infra-Red Object Recognition Using Analytically Designed Low Level Filters for Data Representation},

author = {Maliha Arif and Abhijit Mahalanobis},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICIP_2021__Sparse_Learning-Camera-Ready.pdf},

year  = {2021},

date = {2021-09-19},

publisher = {IEEE International Conference on Image Processing},

abstract = {It is well known that deep convolutional neural networks (CNNs) generalize well over large number of classes when ample training data is available. However, training with smaller datasets does not always achieve robust performance. In such cases, we show that using analytically derived filters in the lowest layer enables a network to achieve better performance than learning from scratch using a relatively small dataset. These class-agnostic filters represent the underlying manifold of the data space, and also generalize to new or unknown classes which may occur on the same manifold. This directly enables new classes to be learned with very few images by simply fine-tuning the final few layers of the network. We illustrate the advantages of our method using the publicly available set of infra-red images of vehicular ground targets. We compare a simple CNN trained using our method with transfer learning performed using the VGG-16 network, and show that when the number of training images is limited, the proposed approach not only achieves better results on the trained classes, but also outperforms a standard network for learning a new object class. 



Index Terms— manifold, eigen representation, few shot learning, sparse learning, infra-red datasets},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{CuellarICIP2021,

title = {Detection of Small Moving Ground Vehicles in Cluttered Terrain Using Infrared Video Imagery},

author = {Adam Cuellar and Abhijit Mahalanobis},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/atc_icip.pdf},

year  = {2021},

date = {2021-09-19},

publisher = {IEEE International Conference on Image Processing},

abstract = {The detection of small moving targets in cluttered infrared imagery remains a difficult and challenging task. Conventional image subtraction techniques with frame-to-frame registration yield very high false alarm rates. Furthermore, state of the art deep convolutional neural networks (DCNNs) such as YOLO and Mask R-CNN also do not work well for this application. We show however, that it is possible to train a CNN to detect moving targets in a stack of stabilized images

by maximizing a target to clutter ratio (TCR) metric. This metric has been previously used for detecting relatively large stationary targets in single images, but not for the purposes of finding small moving targets using multiple frames. Referred to as moving target indicator network (MTINet), the proposed network does not rely on image subtraction, but instead uses depth-wise convolution to learn inter-frame temporal dependencies. We compare the performance of the MTINet to state of the art DCNNs and a statistical anomaly detection algorithm, and propose a combined approach that offers the benefits of both data-driven learning and statistical analysis. 



Index Terms— Detection, Localization, Infrared, CNN },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{McIntosh2020,

title = {Target Detection in Cluttered Environments Using Infra-Red Images},

author = {Bruce McIntosh and Shashanka Venkataramanan and Abhijit Mahalanobis},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/icip2020_photoready.pdf},

year  = {2020},

date = {2020-10-28},

booktitle = {IEEE International Conference on Image Processing},

abstract = {The detection of targets in infra-red imagery is a challenging problem which involves locating small targets in heavily

cluttered environments while maintaining a low false alarm rate. We propose a network that optimizes a “target to clutter

ratio”(TCR) metric defined as the ratio of the output energies produced by the network in response to targets and clutter.

We show that for target detection, it is advantageous to analytically derive the first layer of a CNN to maximize the

TCR metric, and then train the rest of the network to optimize the same cost function. We evaluate the performance of the

resulting network using a public domain MWIR data set released by the US Army’s Night Vision Laboratories, and compare

it to the state-of-the-art detectors such as Faster RCNN and Yolo-v3. Referred to as the TCRNet, the proposed network

demonstrates state of the art results with greater than 30% improvement in probability of detection while reducing

the false alarm rate by more than a factor of 2 when compared to these leading methods. Ablation studies also show that the

proposed approach and metric are superior to learning the entire network from scratch, or using conventional regression

metrics such as the mean square error (MSE). },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Venkataramanan2020,

title = {Attention Guided Anomaly Localization in Images},

author = {Shashanka Venkataramanan and Kuan-Chuan Peng and Rajat Vikram Singh and Abhijit Mahalanobis},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/2813.pdf

https://youtu.be/b-EQr-fGPWo},

year  = {2020},

date = {2020-08-23},

booktitle = {16th European Conference on Computer Vision},

abstract = {Anomaly localization is an important problem in computer vision which involves localizing anomalous regions within images with applications in industrial inspection, surveillance, and medical imaging. This task is challenging due to the small sample size and pixel coverage of the anomaly in real-world scenarios. Most prior works need to use anomalous training images to compute a class-specific threshold to localize anomalies. Without the need of anomalous training images, we propose Convolutional Adversarial Variational autoencoder with Guided Attention (CAVGA), which localizes the anomaly with a convolutional latent variable to preserve the spatial information. In the unsupervised setting, we propose an attention expansion loss where we encourage CAVGA to focus on all normal regions in the image. Furthermore, in the weakly supervised setting we propose a complementary guided attention loss, where we encourage the attention map to focus on all normal regions while minimizing the attention map corresponding to anomalous regions in the image. CAVGA outperforms the state-of-the-art (SOTA) anomaly localization methods on MVTec Anomaly Detection (MVTAD), modified ShanghaiTech Campus (mSTC) and Large-scale Attention based Glaucoma (LAG) datasets in the unsupervised setting and when using only 2% anomalous images in the weakly-supervised setting. CAVGA also outperforms SOTA anomaly detection methods on the MNIST, CIFAR-10, Fashion-MNIST, MVTAD, mSTC and LAG datasets.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Rodriguez2010b,

title = {Automatic recognition of multiple targets with varying velocities using quadratic correlation filters and Kalman filters},

author = {Andres Rodriguez and Jeffrey Panza and B.V.K. Vijaya Kumar and Abhijit Mahalanobis},

year  = {2010},

date = {2010-02-01},

pages = {446-451},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}