Kaustav Kundu

The goal of this paper is to perform 3D object detection from a single monocular image in the domain of autonomous driving. Our method first aims to generate a set of candidate class-specific object proposals, which are then run through a standard CNN pipeline to obtain high-quality object detections. The focus of this paper is on proposal generation. In particular, we propose an energy minimization approach that places object candidates in 3D using the fact that objects should be on the ground-plane. We then score each candidate box projected to the image plane via several intuitive potentials encoding semantic segmentation, contextual information, size and location priors and typical object shape. Our experimental evaluation demonstrates that our object proposal generation approach significantly outperforms all monocular approaches, and achieves the best detection performance on the challenging KITTI benchmark, among published monocular competitors.

The goal of this paper is to generate high-quality 3D object proposals in the con-text of autonomous driving. Our method exploits stereo imagery to place propos-als in the form of 3D bounding boxes. We formulate the problem as minimizing an energy function encoding object size priors, ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. Combined with convolutional neural net (CNN) scoring, our approach outper-forms all existing results on all three KITTI object classes. 1

The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. We then exploit a CNN on top of these proposals to perform object detection. In particular, we employ a convolutional neural net (CNN) that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. When combined with the CNN, our approach outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Furthermore, we experiment also with the setting where LIDAR information is available, and show that using both LIDAR and stereo leads to the best result.

We propose an approach for semi-automatic annotation of object instances. While most current methods treat object segmentation as a pixel-labeling problem, we here cast it as a polygon prediction task, mimicking how most current datasets have been annotated. In particular, our approach takes as input an image crop and sequentially produces vertices of the polygon outlining the object. This allows a human annotator to interfere at any time and correct a vertex if needed, producing as accurate segmentation as desired by the annotator. We show that our approach speeds up the annotation process by a factor of 4.7 across all classes in Cityscapes, while achieving 78:4% agreement in IoU with original ground-truth, matching the typical agreement between human annotators. For cars, our speed-up factor is 7.3 for an agreement of 82:2%. We further show generalization capabilities of our approach to unseen datasets.

Lean Management (LM) represents a complex socio-technical system where both technical and social practices should be consistently implemented and integrated in order to foster a Continuous Improvement (CI) culture. Despite initial gains in operational performances due to the implementation of the most common and well-established Lean techniques, the great majority of the companies approaching Lean Manufacturing fail in achieving sustainable outcomes in the long term, and most of them eventually come back to their traditional way of doing business. Recognized the pivotal role of soft practices, the purpose of this study is to investigate the role played by the human factor in fostering the establishment of a Sustainable Continuous Improvement (SCI) environment. Starting from surveying the literature, a comprehensive framework including all the relevant soft practices related to LM has been developed. Then, authors proposed, for the first time, Decision-Making Trail and Evaluation Laboratory (DEMATEL) analysis applied to soft practices of SCI, that provides an innovative understanding of the relevant soft practices which foster SCI by showing cause-effect association among them. The proposed methodology reveals precious insights for scholars and practitioners who intend to approach and apply SCI. The impact relations map shows that some soft practices are initiators and some others enablers of the SCI and allows to identify the most relevant Critical Success Factors (CSF) and interrelationships amongst them. Results show that the key for a SCI is represented by a full engagement of the workforce, which must be triggered and supported by Top Management with the use of some leverages such as an effective communication, training and use of Kaizen events.