Semantic segmentation of outdoor scenes is problematic when there are variations in imaging conditions. It is known that albedo (reflectance) is invariant to all kinds of illumination effects. Thus, using reflectance images for semantic segmentation task can be favorable. Additionally, not only segmentation may benefit from reflectance, but also segmentation may be useful for reflectance computation. Therefore, in this paper, the tasks of semantic segmentation and intrinsic image decomposition are considered as a combined process by exploring their mutual relationship in a joint fashion. To that end, we propose a supervised end-to-end CNN architecture to jointly learn intrinsic image decomposition and semantic segmentation. We analyze the gains of addressing those two problems jointly. Moreover, new cascade CNN architectures for intrinsic-for-segmentation and segmentation-for-intrinsic are proposed as single tasks. Furthermore, a dataset of 35K synthetic images of natural environments is created with corresponding albedo and shading (intrinsics), as well as semantic labels (segmentation) assigned to each object/scene. The experiments show that joint learning of intrinsic image decomposition and semantic segmentation is beneficial for both tasks for natural scenes. Dataset and models are available at: https://ivi.fnwi.uva.nl/cv/intrinseg.

No abstract

Two major stages of seed development are dormancy and germination which finally promotes the growth of a plant. Some internal and external factors such as hormonal, genetic, chromatin development and environmental factors which maintain the seed dormancy with passing time and other suitable factors, these dormancy promoters are gradually decreased causing release of dormancy and promoting germination by the mechanisms of ROS in plant signalling, cell elongation and reverse mobilization. But dormancy has some benefits in protecting the seed from extreme condition even after natural disaster as well as serving as food for predators in order to maintain balance of nature. So, dormancy can be inhibited by some phytochemical components like terpenoids, polyphenoliic compounds, flavonoids, alkaloids and glycosides by the mechanism of inhibiting water uptake system III and II, surface sterilization, reverse mobilization, cell elongation etc

No abstract

Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems. The scenes are highly structured and semantically different from scenarios seen in nature-centered scenes such as gardens or parks. To promote machine learning methods for natureoriented applications, such as agriculture and gardening, we propose the multimodal synthetic dataset for Enclosed garDEN scenes (EDEN). The dataset features more than 300K images captured from more than 100 garden models. Each image is annotated with various low/high-level vision modalities, including semantic segmentation, depth, surface normals, intrinsic colors, and optical flow. Experimental results on the state-of-the-art methods for semantic segmentation and monocular depth prediction, two important tasks in computer vision, show positive impact of pretraining deep networks on our dataset for unstructured natural scenes. The dataset and related materials will be available at https://lhoangan.github.io/eden.