International Journal of New Developments in Engineering and Society, 2024, 8(1); doi: 10.25236/IJNDES.2024.080102.
Guo Xin
School of Intelligence Science and Engineering, Xi'an Peihua University, Xi'an, 710125, China
The research and development trends in image depth estimation technology based on deep learning methodologies. The study highlights the transition from traditional methods to deep learning approaches, emphasizing the significance of depth estimation in various computer vision applications. Key challenges, including occlusion handling, scale variance, and scene complexity, are discussed, alongside methodological advancements such as single-image depth prediction, stereo depth estimation, and multi-view depth inference. Additionally, the fusion of depth with other modalities, such as RGB-D and RGB-T, is explored. The paper also addresses the challenges of robustness in diverse environmental conditions and computational efficiency for real-time deployment. Applications of image depth estimation technology in robotics, augmented and virtual reality, autonomous driving, and medical imaging are presented, highlighting the transformative impact of deep learning on enhancing depth perception and scene understanding.
Deep learning, Image depth estimation, Convolutional neural networks, Multi-view fusion, Robustness
Guo Xin. Research and Development Trend of Image Depth Estimation Technology Based on Deep Learning. International Journal of New Developments in Engineering and Society (2024) Vol.8, Issue 1: 7-12. https://doi.org/10.25236/IJNDES.2024.080102.
[1] Xiaogang, R., Wenjing, Y., Jing, H., Peiyuan, G., & Wei, G. (2020). Monocular depth estimation based on deep learning: A survey. In 2020 Chinese Automation Congress (CAC) (pp. 2436-2440). IEEE.
[2] Hambarde, P., Dudhane, A., & Murala, S. (2019). Single image depth estimation using deep adversarial training. In 2019 IEEE International Conference on Image Processing (ICIP) (pp. 989-993). IEEE.
[3] Mahmood, F., & Durr, N. J. (2018). Deep learning-based depth estimation from a synthetic endoscopy image training set. In Medical Imaging 2018: Image Processing (Vol. 10574, pp. 521-526). SPIE.
[4] Ming, Y., Meng, X., Fan, C., & Yu, H. (2021). Deep learning for monocular depth estimation: A review. Neurocomputing, 438, 14-33.
[5] Masoumian, A., Rashwan, H. A., Cristiano, J., Asif, M. S., & Puig, D. (2022). Monocular depth estimation using deep learning: A review. Sensors, 22(14), 5353.
[6] Laga, H., Jospin, L. V., Boussaid, F., & Bennamoun, M. (2020). A survey on deep learning techniques for stereo-based depth estimation. IEEE transactions on pattern analysis and machine intelligence, 44(4), 1738-1764.
[7] Khan, F., Salahuddin, S., & Javidnia, H. (2020). Deep learning-based monocular depth estimation methods—a state-of-the-art review. Sensors, 20(8), 2272.
[8] Gur, S., & Wolf, L. (2019). Single image depth estimation trained via depth from defocus cues. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7683-7692).