The PASCAL Visual Object Classes Challenge

We consider the problem of grasping novel objects, specifically objects that are being seen for the first time through vision. Grasping a previously unknown object, one for which a 3-d model is not available, is a challenging problem. Furthermore, even if given a model, one still has to decide where to grasp the object. We present a learning algorithm that neither requires nor tries to build a 3-d model of the object. Given two (or more) images of an object, our algorithm attempts to identify a few points in each image corresponding to good locations at which to grasp the object. This sparse set of points is then triangulated to obtain a 3-d location at which to attempt a grasp. This is in contrast to standard dense stereo, which tries to triangulate every single point in an image (and often fails to return a good 3-d model). Our algorithm for identifying grasp locations from an image is trained by means of supervised learning, using synthetic images for the training set. We demonstrate this approach on two robotic manipulation platforms. Our algorithm successfully grasps a wide variety of objects, such as plates, tape rolls, jugs, cellphones, keys, screwdrivers, staplers, a thick coil of wire, a strangely shaped power horn and others, none of which were seen in the training set. We also apply our method to the task of unloading items from dishwashers.

/pdf/robotic-grasping-of-novel-objects-using-vision-2zwomdq4zp.pdf

Robotic Grasping of Novel Objects using Vision

Full end-to-end text recognition in natural images is a challenging problem that has received much attention recently. Traditional systems in this area have relied on elaborate models incorporating carefully hand-engineered features or large amounts of prior knowledge. In this paper, we take a different route and combine the representational power of large, multilayer neural networks together with recent developments in unsupervised feature learning, which allows us to use a common framework to train highly-accurate text detector and character recognizer modules. Then, using only simple off-the-shelf methods, we integrate these two modules into a full end-to-end, lexicon-driven, scene text recognition system that achieves state-of-the-art performance on standard benchmarks, namely Street View Text and ICDAR 2003.

/pdf/end-to-end-text-recognition-with-convolutional-neural-1tlpcfdx0o.pdf

End-to-end text recognition with convolutional neural networks

In this paper we explore how a structured light depth sensor, in the form of the Microsoft Kinect, can assist with indoor scene segmentation. We use a CRF-based model to evaluate a range of different representations for depth information and propose a novel prior on 3D location. We introduce a new and challenging indoor scene dataset, complete with accurate depth maps and dense label coverage. Evaluating our model on this dataset reveals that the combination of depth and intensity images gives dramatic performance gains over intensity images alone. Our results clearly demonstrate the utility of structured light sensors for scene understanding.

Indoor scene segmentation using a structured light sensor

Multipliers are the most space and power-hungry arithmetic operators of the digital implementation of deep neural networks. We train a set of state-of-the-art neural networks (Maxout networks) on three benchmark datasets: MNIST, CIFAR-10 and SVHN. They are trained with three distinct formats: floating point, fixed point and dynamic fixed point. For each of those datasets and for each of those formats, we assess the impact of the precision of the multiplications on the final error after training. We find that very low precision is sufficient not just for running trained networks but also for training them. For example, it is possible to train Maxout networks with 10 bits multiplications.

Training deep neural networks with low precision multiplications

The problem of object detection and recognition is a notoriously difficult one, and one that has been the focus of much work in the computer vision and robotics communities. Most work has concentrated on systems that operate purely on visual inputs (i.e., images) and largely ignores other sensor modalities. However, despite the great progress made down this track, the goal of high accuracy object detection for robotic platforms in cluttered real-world environments remains elusive. Instead of relying on information from the image alone, we present a method that exploits the multiple sensor modalities available on a robotic platform. In particular, our method augments a 2-d object detector with 3-d information from a depth sensor to produce a “multi-modal object detector.” We demonstrate our method on a working robotic system and evaluate its performance on a number of common household/office objects.

/pdf/integrating-visual-and-range-data-for-robotic-object-1eg2u1c2by.pdf

Integrating Visual and Range Data for Robotic Object Detection

Human object recognition in a physical 3-d environment is still far superior to that of any robotic vision system. We believe that one reason (out of many) for this--one that has not heretofore been significantly exploited in the artificial vision literature--is that humans use a fovea to fixate on, or near an object, thus obtaining a very high resolution image of the object and rendering it easy to recognize. In this paper, we present a novel method for identifying and tracking objects in multiresolution digital video of partially cluttered environments. Our method is motivated by biological vision systems and uses a learned "attentive" interest map on a low resolution data stream to direct a high resolution "fovea." Objects that are recognized in the fovea can then be tracked using peripheral vision. Because object recognition is run only on a small foveal image, our system achieves performance in real-time object recognition and tracking that is well beyond simpler systems.

https://ijcai.org/Proceedings/07/Papers/341.pdf

Peripheral-foveal vision for real-time object recognition and tracking in video

We consider the problem of robotic object detection of such objects as mugs, cups, and staplers in indoor environments. While object detection has made significant progress in recent years, many current approaches involve extremely complex algorithms, and are prohibitively slow when applied to large scale robotic settings. In this paper, we describe an object detection system that is designed to scale gracefully to large data sets and leverages upward trends in computational power (as exemplified by Graphics Processing Unit (GPU) technology) and memory. We show that our GPU-based detector is up to 90 times faster than a well-optimized software version and can be easily trained on millions of examples. Using inexpensive off-the-shelf hardware, it can recognize multiple object types reliably in just a few seconds per frame.

/pdf/scalable-learning-for-object-detection-with-gpu-hardware-jmqe4duh9m.pdf

Paul Baumstarck

Papers

Integrating Visual and Range Data for Robotic Object Detection

Peripheral-foveal vision for real-time object recognition and tracking in video

Scalable learning for object detection with GPU hardware