Related papers: Motion-based Object Segmentation based on Dense RG…

We present DetectFusion, an RGB-D SLAM system that runs in real-time and can robustly handle semantically known and unknown objects that can move dynamically in the scene. Our system detects, segments and assigns semantic class labels to…

Scene flow is the dense 3D reconstruction of motion and geometry of a scene. Most state-of-the-art methods use a pair of stereo images as input for full scene reconstruction. These methods depend a lot on the quality of the RGB images and…

Crowd flow segmentation is an important step in many video surveillance tasks. In this work, we propose an algorithm for segmenting flows in H.264 compressed videos in a completely unsupervised manner. Our algorithm works on motion vectors…

In contrast to traditional cameras, whose pixels have a common exposure time, event-based cameras are novel bio-inspired sensors whose pixels work independently and asynchronously output intensity changes (called "events"), with microsecond…

We segment moving objects in videos by ranking spatio-temporal segment proposals according to "moving objectness": how likely they are to contain a moving object. In each video frame, we compute segment proposals using multiple…

AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not…

For safety-critical robotics applications such as autonomous driving, it is important to detect all required objects accurately in real-time. Motion segmentation offers a solution by identifying dynamic objects from the scene in a…

Unsupervised video object segmentation aims to segment a target object in the video without a ground truth mask in the initial frame. This challenging task requires extracting features for the most salient common objects within a video…

Scene flow estimation is an extremely important task in computer vision to support the perception of dynamic changes in the scene. For robust scene flow, learning-based approaches have recently achieved impressive results using either…

In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for…

Current object segmentation algorithms are based on the hypothesis that one has access to a very large amount of data. In this paper, we aim to segment objects using only tiny datasets. To this extent, we propose a new automatic part-based…

This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model. Existence of dynamic objects in the environment can cause artifacts and traces in current…

As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments,it is…

Observable motion in videos can give rise to the definition of objects moving with respect to the scene. The task of segmenting such moving objects is referred to as motion segmentation and is usually tackled either by aggregating motion…

This paper presents a novel approach for segmenting moving objects in unconstrained environments using guided convolutional neural networks. This guiding process relies on foreground masks from independent algorithms (i.e. state-of-the-art…

Stereo videos for the dynamic scenes often show unpleasant blurred effects due to the camera motion and the multiple moving objects with large depth variations. Given consecutive blurred stereo video frames, we aim to recover the latent…

We present a stereo-based dense mapping algorithm for large-scale dynamic urban environments. In contrast to other existing methods, we simultaneously reconstruct the static background, the moving objects, and the potentially moving but…

We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels. Previous datasets are created by either capturing real…

As we move through the world, the pattern of light projected on our eyes is complex and dynamic, yet we are still able to distinguish between moving and stationary objects. We propose that humans accomplish this by exploiting constraints…

In this paper, we propose a neural network architecture for scale-invariant semantic segmentation using RGB-D images. We utilize depth information as an additional modality apart from color images only. Especially in an outdoor scene which…