Dipto Sarkar

Piyush Yadav, Dipto Sarkar, Dhaval Salwala et al.

Displaying near-real-time traffic information is a useful feature of digital navigation maps. However, most commercial providers rely on privacy-compromising measures such as deriving location information from cellphones to estimate traffic. The lack of an open-source traffic estimation method using open data platforms is a bottleneck for building sophisticated navigation services on top of OpenStreetMap (OSM). We propose a deep learning-based Complex Event Processing (CEP) method that relies on publicly available video camera streams for traffic estimation. The proposed framework performs near-real-time object detection and objects property extraction across camera clusters in parallel to derive multiple measures related to traffic with the results visualized on OpenStreetMap. The estimation of object properties (e.g. vehicle speed, count, direction) provides multidimensional data that can be leveraged to create metrics and visualization for congestion beyond commonly used density-based measures. Our approach couples both flow and count measures during interpolation by considering each vehicle as a sample point and their speed as weight. We demonstrate multidimensional traffic metrics (e.g. flow rate, congestion estimation) over OSM by processing 22 traffic cameras from London streets. The system achieves a near-real-time performance of 1.42 seconds median latency and an average F-score of 0.80.

Piyush Yadav, Dipto Sarkar, Shailesh Deshpande et al.

In this work, we propose an AI-based technique using freely available satellite images like Landsat and Sentinel to create natural features over OSM in congruence with human editors acting as initiators and validators. The method is based on Interactive Machine Learning technique where human inputs are coupled with the machine to solve complex problems efficiently as compare to pure autonomous process. We use a bottom-up approach where a machine learning (ML) pipeline in loop with editors is used to extract classes using spectral signatures of images and later convert them to editable features to create natural features.

Ashish Sureka, Monika Gupta, Dipto Sarkar et al.

We present a case-study on teaching an undergraduate level course on Software Engineering (second year and fifth semester of bachelors program in Computer Science) at a State University (New Delhi, India) using a novel teaching instruction model. Our approach has four main elements: inverted or flipped classroom, studio-based learning, real-client projects and deployment, large team and peer evaluation. We present our motivation and approach, challenges encountered, pedagogical benefits, findings (both positive and negative) and recommendations. Our motivation was to teach Software Engineering using an active learning (significantly increasing the engagement and collaboration with the Instructor and other students in the class), team-work, balance between theory and practice, imparting both technical and managerial skills encountered in real-world and problem-based learning (through an intensive semester-long project). We conduct a detailed survey (anonymous, optional and online) and present the results of student responses. Survey results reveal that for nearly every students (class size: 89) the instruction model was new, interesting and had a positive impact on the motivation in addition to meeting the learning outcome of the course.