Dual CNN Models for Unsupervised Monocular Depth Estimation

Depth estimation can provide tremendous help for object detection, localization, path planning, etc. However, the existing methods based on deep learning have high requirements on computing power and often cannot be directly applied to autonomous moving platforms (AMP). Fifth-generation (5G) mobile and wireless communication systems have attracted the attention of researchers because it provides the network foundation for cloud computing and edge computing, which makes it possible to utilize deep learning method on AMP. This paper proposes a depth prediction method for AMP based on unsupervised learning, which can learn from video sequences and simultaneously estimate the depth structure of the scene and the ego-motion. Compared with the existing unsupervised learning methods, our method makes the spatial correspondence among pixel points consistent with the image area by smoothing the 3D corresponding vector field based on 2D image, which effectively improves the depth prediction ability of the neural network. Our experiments on the KITTI driving dataset demonstrated that our method outperformed other previous learning-based methods. The results on the Apolloscape and Cityscapes datasets show that our proposed method has a strong universality.

show abstract

“…Ref. [32] estimated the depth information in a single image by using two CNN modules on the basis of [15]. Ref.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Learning of Depth from Monocular Videos Using 3D-2D Corresponding Constraints

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The first revolutionary work in this area was AlexNet CNN model [1] which won the ImageNet large‐scale object recognition challenge [2] in 2012. Since then various variants of CNNs have been proposed for different problems such as residual network (ResNet) [3], squeeze and excitation network (SENet) [4] for image classification; regions with CNN (R‐CNN) [5], Fast‐R‐CNN [6], Faster‐R‐CNN [7] for object detection; Mask‐R‐CNN [8] for image segmentation; local bit‐plane decoded Alexnet descriptor [9] for biomedical image retrieval; dual CNN [10] for depth estimation; HybridSN [11], genetic neural network [12] for hyperspectral image (HSI) classification; RCCNet [13] for colon cancer classification etc. The recent works over CNN are image classification [14], medical image analysis [15], deep hashing [16], HSI classification [17, 18], face anti‐spoofing [19, 20], texture classification [21] etc.…”

Section: Introductionmentioning

confidence: 99%

FuSENet: fused squeeze‐and‐excitation network for spectral‐spatial hyperspectral image classification

Roy¹,

Dubey

Chatterjee

et al. 2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

“…To overcome the inherent difficulties in these methods, an alternative is given by estimating the depth without ground truth depths and semantic information. This involves using stereo views to learn depths by reconstruction of images during the training stage in a selfsupervised manner and then using the trained model to find depth from single images (Godard et al, 2017;Repala and Dubey, 2018;Pilzer et al, 2018;Aleotti et al, 2018). Though these methods have proven to decrease the ambiguity in depth estimation from a single image, they have been applied only on indoor or outdoor scenes taken at ground level.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Monocular Depth Estimation From Uav Images

Madhuanand

Nex

Yang

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Depth is an essential component for various scene understanding tasks and for reconstructing the 3D geometry of the scene. Estimating depth from stereo images requires multiple views of the same scene to be captured which is often not possible when exploring new environments with a UAV. To overcome this monocular depth estimation has been a topic of interest with the recent advancements in computer vision and deep learning techniques. This research has been widely focused on indoor scenes or outdoor scenes captured at ground level. Single image depth estimation from aerial images has been limited due to additional complexities arising from increased camera distance, wider area coverage with lots of occlusions. A new aerial image dataset is prepared specifically for this purpose combining Unmanned Aerial Vehicles (UAV) images covering different regions, features and point of views. The single image depth estimation is based on image reconstruction techniques which uses stereo images for learning to estimate depth from single images. Among the various available models for ground-level single image depth estimation, two models, 1) a Convolutional Neural Network (CNN) and 2) a Generative Adversarial model (GAN) are used to learn depth from aerial images from UAVs. These models generate pixel-wise disparity images which could be converted into depth information. The generated disparity maps from these models are evaluated for its internal quality using various error metrics. The results show higher disparity ranges with smoother images generated by CNN model and sharper images with lesser disparity range generated by GAN model. The produced disparity images are converted to depth information and compared with point clouds obtained using Pix4D. It is found that the CNN model performs better than GAN and produces depth similar to that of Pix4D. This comparison helps in streamlining the efforts to produce depth from a single aerial image.

show abstract

Dual CNN Models for Unsupervised Monocular Depth Estimation

Cited by 25 publications

References 22 publications

Unsupervised Learning of Depth from Monocular Videos Using 3D-2D Corresponding Constraints

Unsupervised Learning of Depth from Monocular Videos Using 3D-2D Corresponding Constraints

FuSENet: fused squeeze‐and‐excitation network for spectral‐spatial hyperspectral image classification

Deep Learning for Monocular Depth Estimation From Uav Images

Contact Info

Product

Resources

About