Self-supervised pseudo-colorizing of masked cells.

Self-supervised learning, which is strikingly referred to as the dark matter of intelligence, is gaining more attention in biomedical applications of deep learning. In this work, we introduce a novel self-supervision objective for the analysis of cells in biomedical microscopy images. We propose training deep learning models to pseudo-colorize masked cells. We use a physics-informed pseudo-spectral colormap that is well suited for colorizing cell topology. Our experiments reveal that approximating semantic segmentation by pseudo-colorization is beneficial for subsequent fine-tuning on cell detection. Inspired by the recent success of masked image modeling, we additionally mask out cell parts and train to reconstruct these parts to further enrich the learned representations. We compare our pre-training method with self-supervised frameworks including contrastive learning (SimCLR), masked autoencoders (MAEs), and edge-based self-supervision. We build upon our previous work and train hybrid models for cell detection, which contain both convolutional and vision transformer modules. Our pre-training method can outperform SimCLR, MAE-like masked image modeling, and edge-based self-supervision when pre-training on a diverse set of six fluorescence microscopy datasets. Code is available at: https://github.com/roydenwa/pseudo-colorize-masked-cells.

Continuous Fusion of Motion Data Using an Axis-Angle Rotation Representation with Uniform B-Spline.

The fusion of motion data is key in the fields of robotic and automated driving. Most existing approaches are filter-based or pose-graph-based. By using filter-based approaches, parameters should be set very carefully and the motion data can usually only be fused in a time forward direction. Pose-graph-based approaches can fuse data in time forward and backward directions. However, pre-integration is needed by applying measurements from inertial measurement units. Additionally, both approaches only provide discrete fusion results. In this work, we address this problem and present a uniform B-spline-based continuous fusion approach, which can fuse motion measurements from an inertial measurement unit and pose data from other localization systems robustly, accurately and efficiently. In our continuous fusion approach, an axis-angle is applied as our rotation representation method and uniform B-spline as the back-end optimization base. Evaluation results performed on the real world data show that our approach provides accurate, robust and continuous fusion results, which again supports our continuous fusion concept.

Semantic Evidential Grid Mapping Using Monocular and Stereo Cameras.

Accurately estimating the current state of local traffic scenes is one of the key problems in the development of software components for automated vehicles. In addition to details on free space and drivability, static and dynamic traffic participants and information on the semantics may also be included in the desired representation. Multi-layer grid maps allow the inclusion of all of this information in a common representation. However, most existing grid mapping approaches only process range sensor measurements such as Lidar and Radar and solely model occupancy without semantic states. In order to add sensor redundancy and diversity, it is desired to add vision-based sensor setups in a common grid map representation. In this work, we present a semantic evidential grid mapping pipeline, including estimates for eight semantic classes, that is designed for straightforward fusion with range sensor data. Unlike other publications, our representation explicitly models uncertainties in the evidential model. We present results of our grid mapping pipeline based on a monocular vision setup and a stereo vision setup. Our mapping results are accurate and dense mapping due to the incorporation of a disparity- or depth-based ground surface estimation in the inverse perspective mapping. We conclude this paper by providing a detailed quantitative evaluation based on real traffic scenarios in the KITTI odometry benchmark dataset and demonstrating the advantages compared to other semantic grid mapping approaches.

3D Traffic Scene Understanding From Movable Platforms.

In this paper, we present a novel probabilistic generative model for multi-object traffic scene understanding from movable platforms which reasons jointly about the 3D scene layout as well as the location and orientation of objects in the scene. In particular, the scene topology, geometry, and traffic activities are inferred from short video sequences. Inspired by the impressive driving capabilities of humans, our model does not rely on GPS, lidar, or map knowledge. Instead, it takes advantage of a diverse set of visual cues in the form of vehicle tracklets, vanishing points, semantic scene labels, scene flow, and occupancy grids. For each of these cues, we propose likelihood functions that are integrated into a probabilistic generative model. We learn all model parameters from training data using contrastive divergence. Experiments conducted on videos of 113 representative intersections show that our approach successfully infers the correct layout in a variety of very challenging scenarios. To evaluate the importance of each feature cue, experiments using different feature combinations are conducted. Furthermore, we show how by employing context derived from the proposed method we are able to improve over the state-of-the-art in terms of object detection and object orientation estimation in challenging and cluttered urban environments.

Continuous stereo self-calibration by camera parameter tracking.

This paper presents a consistent framework for continuous stereo self-calibration. Based on a practical analysis of the sensitivity of stereo reconstruction to camera calibration uncertainties, we identify important parameters for self-calibration. We evaluate different geometric constraints for estimation and tracking of these parameters: bundle adjustment with reduced structure representation relating corresponding points in image sequences, the epipolar constraint between stereo image pairs, and trilinear constraints between image triplets. Continuous, recursive calibration refinement is obtained with a robust, adapted iterated extended Kalman filter. To achieve high accuracy, physically relevant geometric optimization criteria are formulated in a Gauss-Helmert type model. The self-calibration framework is tested on an active stereo system. Experiments with synthetic data as well as on natural indoor and outdoor imagery indicate that the different constraints are complementing each other and thus a method combining two of the above constraints is proposed: While reduced order bundle adjustment gives by far the most accurate results (and might suffice on its own in some environments), the epipolar constraint yields instantaneous calibration that is not affected by independently moving objects in the scene. Hence, it expedites and stabilizes the calibration process.