scispace - formally typeset
Search or ask a question
Book ChapterDOI

Rendering Scenes for Simulating Adverse Weather Conditions.

TL;DR: In this article, a novel approach to render foggy and rainy datasets is proposed, where the rain is generated via estimation of the area of the scene image and then computing streak volume and finally overlapping the streaks with the scene images.
Abstract: Most of the object detection schemes do not perform well when the input image is captured in adverse weather. Reason being that the available datasets for training/testing of those schemes didn’t have many images in such weather conditions. Thus in this work, a novel approach to render foggy and rainy datasets is proposed. The rain is generated via estimation of the area of the scene image and then computing streak volume and finally overlapping the streaks with the scene image. As visibility reduces with depth due to fog, rendering of fog must take depth-map into consideration. In the proposed scheme, the depth map is generated from a single image. Then, the fog coefficient is generated by modifying the 3D Perlin noise with respect to the depth map. Further, blending the corresponding density of the fog with the scene image at a particular region based on precomputed intensities at that region. Demo dataset is available in this https://github.com/senprithwish1994/DatasetAdverse.
Citations
More filters
Journal ArticleDOI
TL;DR: Zhang et al. as discussed by the authors investigated the adverse effects of challenging weather on the visual perception system, investigated the robustness of visual perception systems affected by adverse weather through imaging, and proposed a method to evaluate the robusts of object detection model under different weather variations.

2 citations

References
More filters
Proceedings ArticleDOI
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

123,388 citations

Book ChapterDOI
07 Oct 2012
TL;DR: The goal is to parse typical, often messy, indoor scenes into floor, walls, supporting surfaces, and object regions, and to recover support relationships, to better understand how 3D cues can best inform a structured 3D interpretation.
Abstract: We present an approach to interpret the major surfaces, objects, and support relations of an indoor scene from an RGBD image. Most existing work ignores physical interactions or is applied only to tidy rooms and hallways. Our goal is to parse typical, often messy, indoor scenes into floor, walls, supporting surfaces, and object regions, and to recover support relationships. One of our main interests is to better understand how 3D cues can best inform a structured 3D interpretation. We also contribute a novel integer programming formulation to infer physical support relations. We offer a new dataset of 1449 RGBD images, capturing 464 diverse indoor scenes, with detailed annotations. Our experiments demonstrate our ability to infer support relations in complex scenes and verify that our 3D scene cues and inferred support lead to better object segmentation.

4,827 citations

Journal ArticleDOI
TL;DR: A simple but effective image prior - dark channel prior to remove haze from a single input image is proposed, based on a key observation - most local patches in haze-free outdoor images contain some pixels which have very low intensities in at least one color channel.
Abstract: In this paper, we propose a simple but effective image prior-dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of outdoor haze-free images. It is based on a key observation-most local patches in outdoor haze-free images contain some pixels whose intensity is very low in at least one color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high-quality haze-free image. Results on a variety of hazy images demonstrate the power of the proposed prior. Moreover, a high-quality depth map can also be obtained as a byproduct of haze removal.

3,668 citations

Proceedings ArticleDOI
23 Jun 2008
TL;DR: A cost function in the framework of Markov random fields is developed, which can be efficiently optimized by various techniques, such as graph-cuts or belief propagation, and is applicable for both color and gray images.
Abstract: Bad weather, such as fog and haze, can significantly degrade the visibility of a scene. Optically, this is due to the substantial presence of particles in the atmosphere that absorb and scatter light. In computer vision, the absorption and scattering processes are commonly modeled by a linear combination of the direct attenuation and the airlight. Based on this model, a few methods have been proposed, and most of them require multiple input images of a scene, which have either different degrees of polarization or different atmospheric conditions. This requirement is the main drawback of these methods, since in many situations, it is difficult to be fulfilled. To resolve the problem, we introduce an automated method that only requires a single input image. This method is based on two basic observations: first, images with enhanced visibility (or clear-day images) have more contrast than images plagued by bad weather; second, airlight whose variation mainly depends on the distance of objects to the viewer, tends to be smooth. Relying on these two observations, we develop a cost function in the framework of Markov random fields, which can be efficiently optimized by various techniques, such as graph-cuts or belief propagation. The method does not require the geometrical information of the input image, and is applicable for both color and gray images.

2,048 citations

Journal ArticleDOI
TL;DR: A physics-based model is presented that describes the appearances of scenes in uniform bad weather conditions and a fast algorithm to restore scene contrast, which is effective under a wide range of weather conditions including haze, mist, fog, and conditions arising due to other aerosols.
Abstract: Images of outdoor scenes captured in bad weather suffer from poor contrast. Under bad weather conditions, the light reaching a camera is severely scattered by the atmosphere. The resulting decay in contrast varies across the scene and is exponential in the depths of scene points. Therefore, traditional space invariant image processing techniques are not sufficient to remove weather effects from images. We present a physics-based model that describes the appearances of scenes in uniform bad weather conditions. Changes in intensities of scene points under different weather conditions provide simple constraints to detect depth discontinuities in the scene and also to compute scene structure. Then, a fast algorithm to restore scene contrast is presented. In contrast to previous techniques, our weather removal algorithm does not require any a priori scene structure, distributions of scene reflectances, or detailed knowledge about the particular weather condition. All the methods described in this paper are effective under a wide range of weather conditions including haze, mist, fog, and conditions arising due to other aerosols. Further, our methods can be applied to gray scale, RGB color, multispectral and even IR images. We also extend our techniques to restore contrast of scenes with moving objects, captured using a video camera.

1,393 citations