Monocular Depth Estimation by Learning from Heterogeneous Datasets

Gurram, Akhil; Urfalıoḡlu, Onay; Halfaoui, Ibrahim; Bouzaraa, Fahd; López, Antonio

doi:10.1109/ivs.2018.8500683

Cited by 14 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic segmentation and depth estimation have common feature representations. Joint learning of these tasks have shown significant performance gains in (Liu et al, 2018), (Eigen and Fergus, 2015), (Mousavian et al, 2016), (Jafari et al, 2017) and (Gurram et al, 2018). Learning underlying representations between these tasks help the multi-task network alleviate the confusion in predicting semantic boundaries or depth estimation.…”

Section: Methodsmentioning

confidence: 99%

AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

Chennupati

Sistu

Yogamani

et al. 2019

Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the car. Pixel level classification once considered a challenging task which is now becoming mature to be productized in a car. However, semantic annotation is time consuming and quite expensive. Synthetic datasets with domain adaptation techniques have been used to alleviate the lack of large annotated datasets. In this work, we explore an alternate approach of leveraging the annotations of other tasks to improve semantic segmentation. Recently, multi-task learning became a popular paradigm in automated driving which demonstrates joint learning of multiple tasks improves overall performance of each tasks. Motivated by this, we use auxiliary tasks like depth estimation to improve the performance of semantic segmentation task. We propose adaptive task loss weighting techniques to address scale issues in multi-task loss functions which become more crucial in auxiliary tasks. We experimented on automotive datasets including SYNTHIA and KITTI and obtained 3% and 5% improvement in accuracy respectively.1. Construction of auxiliary task learning architecture for semantic segmentation.2. Novel loss function weighting strategy for one main task and one auxiliary task.

show abstract

Section: Methodsmentioning

confidence: 99%

AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

Chennupati

Sistu

Yogamani

et al. 2019

Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

show abstract

“…In contrast to this, SIDE can be posed as a classification problem using quantized depth values [1,19,12]. This allows employing state-of-the-art semantic segmentation methods.…”

Section: Depth Prediction Using a Multi-task Regression And Classificmentioning

confidence: 99%

“…However, by discretizing depth space into intervals, it can be cast as a classification problem [1,19,12]. While this is less intuitive, classification methods have been found to converge faster and more reliably.…”

Section: Introductionmentioning

confidence: 99%

MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

Lukas

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

We introduce MultiDepth, a novel training strategy and convolutional neural network (CNN) architecture that allows approaching single-image depth estimation (SIDE) as a multi-task problem. SIDE is an important part of road scene understanding. It, thus, plays a vital role in advanced driver assistance systems and autonomous vehicles. Best results for the SIDE task so far have been achieved using deep CNNs. However, optimization of regression problems, such as estimating depth, is still a challenging task. For the related tasks of image classification and semantic segmentation, numerous CNN-based methods with robust training behavior have been proposed. Hence, in order to overcome the notorious instability and slow convergence of depth value regression during training, MultiDepth makes use of depth interval classification as an auxiliary task. The auxiliary task can be disabled at test-time to predict continuous depth values using the main regression branch more efficiently. We applied MultiDepth to road scenes and present results on the KITTI depth prediction dataset. In experiments, we were able to show that end-to-end multi-task learning with both, regression and classification, is able to considerably improve training and yield more accurate results.

show abstract

“…In [6] Gurram et al propose a solution which includes training a model on two heterogeneous datasets, one with depth and the other with semantic map labels. Common NN layers are trained alternately on data from either of the datasets.…”

Section: Most Recent Work On Depth Reconstruction Utilize Deepmentioning

confidence: 99%

Double Refinement Network for Efficient Monocular Depth Estimation

Durasov

Romanov²,

Bubnova³

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Monocular depth estimation is the task of obtaining a measure of distance for each pixel using a single image. It is an important problem in computer vision and is usually solved using neural networks. Though recent works in this area have shown significant improvement in accuracy, the state-of-the-art methods tend to require massive amounts of memory and time to process an image. The main purpose of this work is to improve the performance of the latest solutions with no decrease in accuracy. To this end, we introduce the Double Refinement Network architecture. The proposed method achieves state-of-the-art results on the standard benchmark RGB-D dataset NYU Depth v2, while its frames per second rate is significantly higher (up to 18 times speedup per image at batch size 1) and the RAM usage per image is lower.

show abstract

Monocular Depth Estimation by Learning from Heterogeneous Datasets

Cited by 14 publications

References 31 publications

AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

Double Refinement Network for Efficient Monocular Depth Estimation

Contact Info

Product

Resources

About