Asim Munawar

Real-Time Barcode Detection in the Wild

The linear 1D barcode is the main tagging system for billions of products sold each day. Barcodes have many advantages but require a laser scanner for fast and robust scanning. Solutions exist to read barcodes from cell phones but they assume a carefully framed image within the field of view. This undermines the true potential of barcodes in a wide range of scenarios. In this paper we present a real time technique to detect barcodes in the wild from video streams. Our technique outperforms the state-of-the-art passive techniques both in accuracy and speed. Potential commercial applications enabled by such passive scanning system are also discussed in this paper.

Real-time small obstacle detection on highways using compressive RBM road reconstruction

Small objects on the road can become hazardous obstacles when driving at high speed. Detecting such obstacles is vital to guaranty the safety of self-driving car users, especially on highways. Such tasks cannot be performed using existing active sensors such as radar or LIDAR due to their limited range and resolution at long distances. In this paper we propose a technique to detect anomalous patches on the road from color images using a Restricted Boltzman Machine neural network specifically trained to reconstruct the appearance of the road. The differences between the observed and reconstructed road patches yield a more relevant segmentation of anomalies than classic image processing techniques. We evaluated our technique on texture-based synthetic datasets as well as on real video footage of anomalous objects on highways.

Spatio-Temporal Anomaly Detection for Industrial Robots through Prediction in Unsupervised Feature Space

Spatio-temporal anomaly detection by unsupervised learning have applications in a wide range of practical settings. In this paper we present a surveillance system for industrial robots using a monocular camera. We propose a new unsupervised learning method to train a deep feature extractor from unlabeled images. Without any data augmentation, the algorithm co-learns the network parameters on different pseudo-classes simultaneously to create unbiased feature representation. Combining the learned features with a prediction system, we can detect irregularities in high dimensional data feed (e.g. video of a robot performing pick and place task). The results show how the proposed approach can detect previously unseen anomalies in the robot surveillance video. Although the technique is not designed for classification, we show the use of the learned features in a more traditional classification application for CIFAR-10 dataset.

ISOMER: integrated selection, partitioning, and placement methodology for reconfigurable architectures

Quality system design on dynamic partially reconfigurable platform needs exploration of a vast and multidimensional design space for (1) selection among implementation variants of hardware accelerators, (2) partitioning the reconfigurable fabric, and (3) their placement on the reconfigurable fabric partitions. This paper presents a novel methodology ISOMER for integrated solution of selection, partitioning and placement for performance optimization. Architecture under consideration is a general purpose processor coupled with reconfigurable fabric that can be partitioned in multi-sized partially reconfigurable bins. Our methodology determines performance-efficient partitioning and usage of reconfigurable fabric. Extensive evaluation illustrates that our methodology is scalable and outperforms state-of-the-art techniques for non-partially reconfigurable architectures.

Structural inpainting of road patches for anomaly detection

Obstacle detection on the road is a key function for self-driving vehicles. A lot of research has focused on detecting large obstacles such as cars and pedestrians. Small obstacles can also be the source of serious accidents, especially at high speed. We present an approach for detecting anomalies on the road using a higher-order Boltzmann machine. As opposed to conventional anomaly detectors the proposed system learns to inpaint the road patches with commonly occurring road features such as lane markings and expansion dividers, depending on the context. The system does not consider these frequent road artifacts as anomalies and significantly reduces the number of obstacle candidates. We show initial empirical results for anomaly detection with this new approach.

On-time data exchange in fully-parallelized co-simulation with conservative synchronization

Trade-offs between simulation speed, fidelity, compatibility, and scalability limits the use of accurate high-resolution simulators in the automotive industry. With a growing demand for fuel-efficient and environmentally friendly vehicles, the need for precise co-simulation of entire vehicle is greater than ever before. In this paper we present a technique for distributed discrete event co-simulation that exploits parallel computing and distributed simulation with an advanced synchronization technique to overcome all of these constraints. The system allows us to add new components with their own solvers to a simulation without compromising the solution accuracy or simulation speed.

Human-Like Hand Reaching by Motion Prediction Using Long Short-Term Memory

An interaction between a robot and a human could be difficult with only reactive mechanisms, especially in a social interaction, because the robot usually needs time to plan its movement. This paper discusses a motion generation system for humanoid robots to perform interactions with human motion prediction. To learn a human motion, a Long Short-Term Memory is trained using a public dataset. The effectiveness of the proposed technique is demonstrated by performing a handshake with a humanoid robot. Instead of following the human palm, the robot learns to predict the hand-meeting point. By using three metrics namely the smoothness, timeliness, and efficiency of the robot movements, the experimental results of various motion plans are compared. The predictive method shows a balanced trade-off point in all the metrics.

Low-computation egocentric barcode detector for the blind

Linear barcodes are the principal labeling system for retail products. Barcode reader apps found on smartphones always assume that the localization and framing of the barcode is performed manually by a sighted human operator. This is problematic for visually-impaired people since they dont know where to position the camera to scan the barcode. To solve this problem we propose a hand-free interface to detect barcode using a wearable camera. The user rotate a query product in front of him/her and is informed when and where the barcode is visible. The challenge is to detect small barcodes at arms length in a video with potentially large motion blur. In this paper we propose a novel technique for barcode detection using very little computation (adapted to wearable systems), presenting very good robustness to blur and size variations, and able to run on HD video streams. The proposed system perform significantly better than the state-of-the-art methods on existing public datasets, while being much faster. A new and challenging egocentric product video dataset is also provided with this paper.

Scalable Co-Simulation of Functional Models With Accurate Event Exchange

Recent trends in the automotive industry have forced OEMs and suppliers to adopt simulation-driven development processes. To meet the demands of the rapidly changing industry, simulation technologies must innovate to provide faster and accurate simulations of increasingly complex models. In this paper we present a set of technologies that were developed to provide a no-compromise, high fidelity, scalable simulation of heterogeneous functional models. Using our new technology we were able to produce more accurate results in orders of magnitude less time than other frequently used techniques in the industry. The proposed approach to co-simulation allows us to perform functional simulation of full-vehicle without sacrificing the solution accuracy or simulation speed.