Anuj Sharma

Md Zahid Hasan, Jiajing Chen, Jiyang Wang et al.

Recognizing the activities causing distraction in real-world driving scenarios is critical for ensuring the safety and reliability of both drivers and pedestrians on the roadways. Conventional computer vision techniques are typically data-intensive and require a large volume of annotated training data to detect and classify various distracted driving behaviors, thereby limiting their efficiency and scalability. We aim to develop a generalized framework that showcases robust performance with access to limited or no annotated training data. Recently, vision-language models have offered large-scale visual-textual pretraining that can be adapted to task-specific learning like distracted driving activity recognition. Vision-language pretraining models, such as CLIP, have shown significant promise in learning natural language-guided visual representations. This paper proposes a CLIP-based driver activity recognition approach that identifies driver distraction from naturalistic driving images and videos. CLIP's vision embedding offers zero-shot transfer and task-based finetuning, which can classify distracted activities from driving video data. Our results show that this framework offers state-of-the-art performance on zero-shot transfer and video-based CLIP for predicting the driver's state on two public datasets. We propose both frame-based and video-based frameworks developed on top of the CLIP's visual representation for distracted driving detection and classification tasks and report the results.

Armstrong Aboah, Yaw Adu-Gyamfi, Senem Velipasalar Gursoy et al.

The current paper implements a methodology for automatically detecting vehicle maneuvers from vehicle telemetry data under naturalistic driving settings. Previous approaches have treated vehicle maneuver detection as a classification problem, although both time series segmentation and classification are required since input telemetry data is continuous. Our objective is to develop an end-to-end pipeline for frame-by-frame annotation of naturalistic driving studies videos into various driving events including stop and lane keeping events, lane changes, left-right turning movements, and horizontal curve maneuvers. To address the time series segmentation problem, the study developed an Energy Maximization Algorithm (EMA) capable of extracting driving events of varying durations and frequencies from continuous signal data. To reduce overfitting and false alarm rates, heuristic algorithms were used to classify events with highly variable patterns such as stops and lane-keeping. To classify segmented driving events, four machine learning models were implemented, and their accuracy and transferability were assessed over multiple data sources. The duration of events extracted by EMA were comparable to actual events, with accuracies ranging from 59.30% (left lane change) to 85.60% (lane-keeping). Additionally, the overall accuracy of the 1D-convolutional neural network model was 98.99%, followed by the Long-short-term-memory model at 97.75%, then random forest model at 97.71%, and the support vector machine model at 97.65%. These model accuracies where consistent across different data sources. The study concludes that implementing a segmentation-classification pipeline significantly improves both the accuracy for driver maneuver detection and transferability of shallow and deep ML models across diverse datasets.

Mohammed Shaiqur Rahman, Jiyang Wang, Senem Velipasalar Gursoy et al.

This article presents a synthetic distracted driving (SynDD2 - a continuum of SynDD1) dataset for machine learning models to detect and analyze drivers' various distracted behavior and different gaze zones. We collected the data in a stationary vehicle using three in-vehicle cameras positioned at locations: on the dashboard, near the rearview mirror, and on the top right-side window corner. The dataset contains two activity types: distracted activities and gaze zones for each participant, and each activity type has two sets: without appearance blocks and with appearance blocks such as wearing a hat or sunglasses. The order and duration of each activity for each participant are random. In addition, the dataset contains manual annotations for each activity, having its start and end time annotated. Researchers could use this dataset to evaluate the performance of machine learning algorithms to classify various distracting activities and gaze zones of drivers.

Lalita Kumari, Sukhdeep Singh, VVS Rathore et al.

The handwritten text recognition problem is widely studied by the researchers of computer vision community due to its scope of improvement and applicability to daily lives, It is a sub-domain of pattern recognition. Due to advancement of computational power of computers since last few decades neural networks based systems heavily contributed towards providing the state-of-the-art handwritten text recognizers. In the same direction, we have taken two state-of-the art neural networks systems and merged the attention mechanism with it. The attention technique has been widely used in the domain of neural machine translations and automatic speech recognition and now is being implemented in text recognition domain. In this study, we are able to achieve 4.15% character error rate and 9.72% word error rate on IAM dataset, 7.07% character error rate and 16.14% word error rate on GW dataset after merging the attention and word beam search decoder with existing Flor et al. architecture. To analyse further, we have also used system similar to Shi et al. neural network system with greedy decoder and observed 23.27% improvement in character error rate from the base model.

Lalita Kumari, Sukhdeep Singh, Vaibhav Varish Singh Rathore et al.

In this study, we have presented an efficient procedure using two state-of-the-art approaches from the literature of handwritten text recognition as Vertical Attention Network and Word Beam Search. The attention module is responsible for internal line segmentation that consequently processes a page in a line-by-line manner. At the decoding step, we have added a connectionist temporal classification-based word beam search decoder as a post-processing step. In this study, an end-to-end paragraph recognition system is presented with a lexicon decoder as a post-processing step. Our procedure reports state-of-the-art results on standard datasets. The reported character error rate is 3.24% on the IAM dataset with 27.19% improvement, 1.13% on RIMES with 40.83% improvement and 2.43% on the READ-16 dataset with 32.31% improvement from existing literature and the word error rate is 8.29% on IAM dataset with 43.02% improvement, 2.94% on RIMES dataset with 56.25% improvement and 7.35% on READ-2016 dataset with 47.27% improvement from the existing results. The character error rate and word error rate reported in this work surpass the results reported in the literature.

Lalita Kumari, Sukhdeep Singh, VVS Rathore et al.

Cursive handwritten text recognition is a challenging research problem in the domain of pattern recognition. The current state-of-the-art approaches include models based on convolutional recurrent neural networks and multi-dimensional long short-term memory recurrent neural networks techniques. These methods are highly computationally extensive as well model is complex at design level. In recent studies, combination of convolutional neural network and gated convolutional neural networks based models demonstrated less number of parameters in comparison to convolutional recurrent neural networks based models. In the direction to reduced the total number of parameters to be trained, in this work, we have used depthwise convolution in place of standard convolutions with a combination of gated-convolutional neural network and bidirectional gated recurrent unit to reduce the total number of parameters to be trained. Additionally, we have also included a lexicon based word beam search decoder at testing step. It also helps in improving the the overall accuracy of the model. We have obtained 3.84% character error rate and 9.40% word error rate on IAM dataset; 4.88% character error rate and 14.56% word error rate in George Washington dataset, respectively.

Ujjwal Thakur, Anuj Sharma

Offline Handwritten Mathematical Expression Recognition (HMER) is a major area in the field of mathematical expression recognition. Offline HMER is often viewed as a much harder problem as compared to online HMER due to a lack of temporal information and variability in writing style. In this paper, we purpose a encoder-decoder model that uses paired adversarial learning. Semantic-invariant features are extracted from handwritten mathematical expression images and their printed mathematical expression counterpart in the encoder. Learning of semantic-invariant features combined with the DenseNet encoder and transformer decoder, helped us to improve the expression rate from previous studies. Evaluated on the CROHME dataset, we have been able to improve latest CROHME 2019 test set results by 4% approx.

Vinod Kumar Chauhan, Sukhdeep Singh, Anuj Sharma

Handwritten character recognition (HCR) remains a challenging pattern recognition problem despite decades of research, and lacks research on script independent recognition techniques. {\color{black}This is mainly because of similar character structures, different handwriting styles, diverse scripts, handcrafted feature extraction techniques, unavailability of data and code, and the development of script-specific deep learning techniques. To address these limitations, we have proposed a script independent deep learning network for HCR research, called HCR-Net, that sets a new research direction for the field. HCR-Net is based on a novel transfer learning approach for HCR, which \textit{partly utilizes} feature extraction layers of a pre-trained network.} Due to transfer learning and image augmentation, HCR-Net provides faster and computationally efficient training, better performance and generalizations, and can work with small datasets. HCR-Net is extensively evaluated on 40 publicly available datasets of Bangla, Punjabi, Hindi, English, Swedish, Urdu, Farsi, Tibetan, Kannada, Malayalam, Telugu, Marathi, Nepali and Arabic languages, and established 26 new benchmark results while performed close to the best results in the rest cases. HCR-Net showed performance improvements up to 11\% against the existing results and achieved a fast convergence rate showing up to 99\% of final performance in the very first epoch. HCR-Net significantly outperformed the state-of-the-art transfer learning techniques and also reduced the number of trainable parameters by 34\% as compared with the corresponding pre-trained network. To facilitate reproducibility and further advancements of HCR research, the complete code is publicly released at \url{https://github.com/jmdvinodjmd/HCR-Net}.

James Gunn, Zygmunt Lenyk, Anuj Sharma et al.

Combining complementary sensor modalities is crucial to providing robust perception for safety-critical robotics applications such as autonomous driving (AD). Recent state-of-the-art camera-lidar fusion methods for AD rely on monocular depth estimation which is a notoriously difficult task compared to using depth information from the lidar directly. Here, we find that this approach does not leverage depth as expected and show that naively improving depth estimation does not lead to improvements in object detection performance. Strikingly, we also find that removing depth estimation altogether does not degrade object detection performance substantially, suggesting that relying on monocular depth could be an unnecessary architectural bottleneck during camera-lidar fusion. In this work, we introduce a novel fusion method that bypasses monocular depth estimation altogether and instead selects and fuses camera and lidar features in a bird's-eye-view grid using a simple attention mechanism. We show that our model can modulate its use of camera features based on the availability of lidar features and that it yields better 3D object detection on the nuScenes dataset than baselines relying on monocular depth estimation.

Alexandru Buburuzan, Anuj Sharma, John Redford et al.

Safety-critical applications, such as autonomous driving, require extensive multimodal data for rigorous testing. Methods based on synthetic data are gaining prominence due to the cost and complexity of gathering real-world data but require a high degree of realism and controllability in order to be useful. This paper introduces MObI, a novel framework for Multimodal Object Inpainting that leverages a diffusion model to create realistic and controllable object inpaintings across perceptual modalities, demonstrated for both camera and lidar simultaneously. Using a single reference RGB image, MObI enables objects to be seamlessly inserted into existing multimodal scenes at a 3D location specified by a bounding box, while maintaining semantic consistency and multimodal coherence. Unlike traditional inpainting methods that rely solely on edit masks, our 3D bounding box conditioning gives objects accurate spatial positioning and realistic scaling. As a result, our approach can be used to insert novel objects flexibly into multimodal scenes, providing significant advantages for testing perception models.

Lalita Kumari, Sukhdeep Singh, Vaibhav Varish Singh Rathore et al.

The Handwritten Text Recognition problem has been a challenge for researchers for the last few decades, especially in the domain of computer vision, a subdomain of pattern recognition. Variability of texts amongst writers, cursiveness, and different font styles of handwritten texts with degradation of historical text images make it a challenging problem. Recognizing scanned document images in neural network-based systems typically involves a two-step approach: segmentation and recognition. However, this method has several drawbacks. These shortcomings encompass challenges in identifying text regions, analyzing layout diversity within pages, and establishing accurate ground truth segmentation. Consequently, these processes are prone to errors, leading to bottlenecks in achieving high recognition accuracies. Thus, in this study, we present an end-to-end paragraph recognition system that incorporates internal line segmentation and gated convolutional layers based encoder. The gating is a mechanism that controls the flow of information and allows to adaptively selection of the more relevant features in handwritten text recognition models. The attention module plays an important role in performing internal line segmentation, allowing the page to be processed line-by-line. During the decoding step, we have integrated a connectionist temporal classification-based word beam search decoder as a post-processing step. In this work, we have extended existing LexiconNet by carefully applying and utilizing gated convolutional layers in the existing deep neural network. Our results at line and page levels also favour our new GatedLexiconNet. This study reported character error rates of 2.27% on IAM, 0.9% on RIMES, and 2.13% on READ-16, and word error rates of 5.73% on IAM, 2.76% on RIMES, and 6.52% on READ-2016 datasets.

Sukhdeep Singh, Anuj Sharma, Vinod Kumar Chauhan · oxford

Graph Neural Networks (GNN) have emerged as a popular and standard approach for learning from graph-structured data. The literature on GNN highlights the potential of this evolving research area and its widespread adoption in real-life applications. However, most of the approaches are either new in concept or derived from specific techniques. Therefore, the potential of more than one approach in hybrid form has not been studied extensively, which can be well utilized for sequenced data or static data together. We derive a hybrid approach based on two established techniques as generalized aggregation networks and topology adaptive graph convolution networks that solve our purpose to apply on both types of sequenced and static nature of data, effectively. The proposed method applies to both node and graph classification. Our empirical analysis reveals that the results are at par with literature results and better for handwritten strokes as sequenced data, where graph structures have not been explored.

Udita Jana, Jyoti Prakash Das Karmakar, Pranamesh Chakraborty et al.

Movement specific vehicle classification and counting at traffic intersections is a crucial component for various traffic management activities. In this context, with recent advancements in computer-vision based techniques, cameras have emerged as a reliable data source for extracting vehicular trajectories from traffic scenes. However, classifying these trajectories by movement type is quite challenging as characteristics of motion trajectories obtained this way vary depending on camera calibrations. Although some existing methods have addressed such classification tasks with decent accuracies, the performance of these methods significantly relied on manual specification of several regions of interest. In this study, we proposed an automated classification method for movement specific classification (such as right-turn, left-turn and through movements) of vision-based vehicle trajectories. Our classification framework identifies different movement patterns observed in a traffic scene using an unsupervised hierarchical clustering technique Thereafter a similarity-based assignment strategy is adopted to assign incoming vehicle trajectories to identified movement groups. A new similarity measure was designed to overcome the inherent shortcomings of vision-based trajectories. Experimental results demonstrated the effectiveness of the proposed classification approach and its ability to adapt to different traffic scenarios without any manual intervention.

Armstrong Aboah, Maged Shoman, Vishal Mandal et al.

Any intelligent traffic monitoring system must be able to detect anomalies such as traffic accidents in real time. In this paper, we propose a Decision-Tree - enabled approach powered by Deep Learning for extracting anomalies from traffic cameras while accurately estimating the start and end time of the anomalous event. Our approach included creating a detection model, followed by anomaly detection and analysis. YOLOv5 served as the foundation for our detection model. The anomaly detection and analysis step entail traffic scene background estimation, road mask extraction, and adaptive thresholding. Candidate anomalies were passed through a decision tree to detect and analyze final anomalies. The proposed approach yielded an F1 score of 0.8571, and an S4 score of 0.5686, per the experimental validation.

Anuj sharma, Shubhamoy Dey

Sentiment analysis or opinion mining has become an open research domain after proliferation of Internet and Web 2.0 social media. People express their attitudes and opinions on social media including blogs, discussion forums, tweets, etc. and, sentiment analysis concerns about detecting and extracting sentiment or opinion from online text. Sentiment based text classification is different from topical text classification since it involves discrimination based on expressed opinion on a topic. Feature selection is significant for sentiment analysis as the opinionated text may have high dimensions, which can adversely affect the performance of sentiment analysis classifier. This paper explores applicability of feature selection methods for sentiment analysis and investigates their performance for classification in term of recall, precision and accuracy. Five feature selection methods (Document Frequency, Information Gain, Gain Ratio, Chi Squared, and Relief-F) and three popular sentiment feature lexicons (HM, GI and Opinion Lexicon) are investigated on movie reviews corpus with a size of 2000 documents. The experimental results show that Information Gain gave consistent results and Gain Ratio performs overall best for sentimental feature selection while sentiment lexicons gave poor performance. Furthermore, we found that performance of the classifier depends on appropriate number of representative feature selected from text.

Anuj Sharma, Shubhamoy Dey

Web 2.0 services have enabled people to express their opinions, experience and feelings in the form of user-generated content. Sentiment analysis or opinion mining involves identifying, classifying and aggregating opinions as per their positive or negative polarity. This paper investigates the efficacy of different implementations of Self-Organizing Maps (SOM) for sentiment based visualization and classification of online reviews. Specifically, this paper implements the SOM algorithm for both supervised and unsupervised learning from text documents. The unsupervised SOM algorithm is implemented for sentiment based visualization and classification tasks. For supervised sentiment analysis, a competitive learning algorithm known as Learning Vector Quantization is used. Both algorithms are also compared with their respective multi-pass implementations where a quick rough ordering pass is followed by a fine tuning pass. The experimental results on the online movie review data set show that SOMs are well suited for sentiment based classification and sentiment polarity visualization.