Christoph HeindlProfactor GmbH · Visual Computing
Christoph Heindl
About
35
Publications
4,177
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
169
Citations
Citations since 2017
Introduction
I'am a computer vision scientist working in the fields of 3D reconstruction, deep learning and robotics. Creator of real-time 3d scanner http://reconstructme.net
Publications
Publications (35)
This paper is a technical description of a novel Augmented Reality application in the industrial domain of furniture production. In the presented case, workers suffered from high cognitive load in doing end-of-line quality inspection and individual handling of a high variety of products. The proposed solution consists of a Spatial Augmented Reality...
Ergonomic and economic factors are important for the design of modern industrial workplaces. Planning tools such as digital models of human motion or motion capturing by video can assist in simulations, monitoring, analyzing and final design of work processes. Combining simulation and motion capture reaps the respective benefits of each approach. A...
Solving complex computer vision tasks by deep learning techniques rely on large amounts of (supervised) image data, typically unavailable in industrial environments. Consequently, the lack of training data is beginning to impede the successful transfer of state-of-the-art computer vision methods to industrial applications. We introduce BlendTorch,...
Solving complex computer vision tasks by deep learning techniques relies on large amounts of (supervised) image data, typically unavailable in industrial environments. The lack of training data starts to impede the successful transfer of state-of-the-art methods in computer vision to industrial applications. We introduce BlendTorch, an adaptive Dom...
The success of deep learning has revolutionized many fields of research including areas of computer vision, text and speech processing. Enormous research efforts have led to numerous methods that are capable of efficiently analyzing data, especially in the Euclidean space. However, many problems are posed in non-Euclidean domains modeled as general...
Automated fiber placement (AFP) is an advanced manufacturing technology that increases the rate of production of composite materials. At the same time, the need for adaptable and fast inline control methods of such parts raises. Existing inspection systems make use of handcrafted filter chains and feature detectors, tuned for a specific measurement...
The rapid growth of collaborative robotics in production requires new automation technologies that take human and machine equally into account. In this work, we describe a monocular camera based system to detect human-machine interactions from a bird's-eye perspective. Our system predicts poses of humans and robots from a single wide-angle color im...
The raise of collaborative robotics has led to wide range of sensor technologies to detect human-machine interactions: at short distances, proximity sensors detect nontactile gestures virtually occlusion-free, while at medium distances, active depth sensors are frequently used to infer human intentions. We describe an optical system for large works...
In this work we investigate the coordination of human-machine interactions from a bird's-eye view using a single panoramic color camera. Our approach replaces conventional physical hardware sensors, such as light barriers and switches, by location-aware virtual regions. We employ recent methods from the field of pose estimation to detect human and...
This work considers robot keypoint estimation on color images as a supervised machine learning task. We propose the use of probabilistically created renderings to overcome the lack of labeled real images. Rather than sampling from stationary distributions, our approach introduces a feedback mechanism that constantly adapts probability distributions...
Commodity RGB-D sensors capture color images along with dense pixel-wise depth information in real-time. Typical RGB-D sensors are provided with a factory calibration and exhibit erratic depth readings due to coarse calibration values, ageing and thermal influence effects. This limits their applicability in computer vision and robotics. We propose...
We propose a novel 3D human pose detector using two panoramic cameras. We show that transforming fisheye perspectives to rectilinear views allows a direct application of two-dimensional deep-learning pose estimation methods, without the explicit need for a costly re-training step to compensate for fisheye image distortions. By utilizing panoramic c...
This paper considers the task of locating articulated poses of multiple robots in images. Our approach simultaneously infers the number of robots in a scene, identifies joint locations and estimates sparse depth maps around joint locations. The proposed method applies staged convolutional feature detectors to 2D image inputs and computes robot inst...
Recent advances in low cost RGB-D sensors and progress in reconstruction approaches paves way for creating real-time 3D models of people. It is equally important to enhance the visual appeal of such 3D models with textures. Most of the existing approaches use per-vertex colors, such that the color resolution is limited to mesh resolution. In this p...
In this paper, a robust, real-time object tracking approach capable of dealing with multiple symmetric and non-symmetric objects in a real-time requirement setting is proposed. The approach relies only on depth data to track multiple objects in a dynamic environment and uses random-forest based learning to deal with problems like object occlusion,...
Human action recognition plays a vital role in the field of human-robot interaction and is widely researched for its potential applications. In this paper we propose a human action recognition framework for human robot interaction in industrial applications. First, a set of key descriptors are learned from a collection of weak spatio-temporal skele...
human action recognition plays a vital role in the field of human-robot interaction and is widely researched for its potential applications. In this paper we propose a human action recognition framework for human robot interaction in industrial applications. The approach learns a set of key descriptors from a collection of weak spatio-temporal skel...
human action recognition plays a vital role in the field of human-robot interaction and is widely researched for its potential applications. In this paper we propose a human action recognition framework using 3D depth data for human-robot interaction in industrial applications. The approach learns a set of key descriptors from a collection of weak...
This paper presents system architecture, model-ing, control and experimental results of a fully autonomous unmanned aerial vehicle (UAV). Standard autopilot systems rely on external references for navigation. Outdoor systems often utilize (differential) global position systems (GPS), while indoor systems rely on indoor tracking systems. A low-cost...
Automated packaging is becoming more and more interesting for production sites. However, in many companies the packaging process can only handle a limited amount of products. Most of the time for new products, the packaging system needs to be modified. One of the main components in an automated packaging process is the grasping of the objects that...
Today’s markets and economies are becoming increasingly volatile, unpredictable, they are changing radically and even the
innovation speed is accelerating. Manufacturing and production technology and systems must keep pace with this trend. The
impact of novel innovative 3D imaging technology to counter these radical changes is exemplarily shown on...
The paper gives an overview of a novel innovative vision system embedded in manufacturing applications. The system is able to handle (1) unknown products, (2) in-available data, (3) large disturbances and deviations (shape, position, or even part type) and (4) even very small lot-sizes. The concept foresees a full integration into production techno...
Building to order implies responding to individual customer requests, not simply producing large numbers of goods for stock and encouraging their sale by promotion and discounting. The paint shop is one of the biggest bottlenecks in production today. Adapting state-of-the-art robotized painting lines to new variants is time-consuming and leaving th...
Projects
Project (1)
LERN4MRK: Modeling, learning and abstracting processes for human-robot cooperation
In industrial robotics, the trend of the past few years has been to collaborative lightweight construction robots. In comparison to conventional robotics, they are more cost-effective to purchase, more flexible and easier to use. The combination of machine learning techniques has recently opened up new fields of application for human robot interaction. Despite the scientific successes of recent years, important questions remain unanswered. These concern, include
• the adaptability to dynamic environmental conditions
• the flexibility in the execution of activities in the event of a changing task
• the understanding or cognitive models of the task and the relationships with the environmental factors
The necessity for such adaptation processes results from the economic conditions. Although the modality of programming (kinesthetic teaching, mixed reality methods, etc.) has greatly improved, the generalization capabilities of such approaches on the process and execution level are very limited. The project LERN4MRK addresses the transfer of manual human activities to the robot or a product / process variant to a similar one. In the case of robotics, this transfer implies
(a) the mapping of motion patterns, and
(b) the ability to adapt to the process parameters (for example, product variants but similar process variants)
The project is focused on the area of "transfer learning" from previously manual activities to flexible automation.
