Real-Time Single Image Depth Perception in the Wild with Handheld Devices

Aleotti, Filippo; Zaccaroni, Giulio; Bartolomei, Luca; Poggi, Matteo; Tosi, Fabio; Mattoccia, Stefano

doi:10.3390/s21010015

Cited by 44 publications

(31 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One simple alternative is employing lightweight architectures such as MobileNet [24,25,49,55], GhostNet [21], and FBNet [54]. One popular approach is utilizing network compression techniques, including quantization [22], network pruning [58], and knowledge distillation [60,1]. Other methods employing well-known pyramid networks or dynamic optimization schemes.…”

Section: Related Workmentioning

confidence: 99%

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

Huynh¹,

Nguyen²,

Matas³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture search (NAS) approaches, where finding optimized networks is computationally highly demanding, the introduced novel Assisted Tabu Search leads to efficient architecture exploration. Moreover, we construct the search space on a pre-defined backbone network to balance layer diversity and search space size. The LiDNAS method outperforms the state-of-the-art NAS approach, proposed for disparity and depth estimation, in terms of search efficiency and output model performance. The LiDNAS optimized models achieve result superior to compact depth estimation state-of-the-art on NYU-Depth-v2, KITTI, and Scan-Net, while being 7%-500% more compact in size, i.e the number of model parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

Huynh¹,

Nguyen²,

Matas³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To reduce inference times, there exist two primary avenues outside of increasing compute resources: model size reduction and platform-specific optimizations. To reduce the size of our depth estimation model, we leverage the knowledge distillation techniques proposed in [8]. Knowledge distillation is the process of training a smaller, student network to learn the function represented by a larger, teacher network via a semi-supervised learning scheme.…”

Section: A Depth Estimationmentioning

confidence: 99%

“…In our knowledge distillation pipeline, we used the MiDaS network developed in [6] as the teacher network. For the student architecture, we employed the same architecture from [8]. The student network output was then regressed to match the output of the MiDaS network on our curated dataset.…”

Section: A Depth Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Subsystem for Autonomous Collision Avoidance on a small UAS with Embedded GPU

Polosky¹,

Gwin²,

Furman³

et al. 2021

Preprint

View full text Add to dashboard Cite

Interest in unmanned aerial system (UAS) powered solutions for 6G communication networks has grown immensely with the widespread availability of machine learning based autonomy modules and embedded graphical processing units (GPUs). While these technologies have revolutionized the possibilities of UAS solutions, designing an operable, robust autonomy framework for UAS remains a multi-faceted and difficult problem. In this work, we present our novel, modular framework for UAS autonomy, entitled MR-iFLY, and discuss how it may be extended to enable 6G swarm solutions. We begin by detailing the challenges associated with machine learning based UAS autonomy on resource constrained devices. Next, we describe in depth, how MR-iFLY's novel depth estimation and collision avoidance technology meets these challenges. Lastly, we describe the various evaluation criteria we have used to measure performance, show how our optimized machine vision components provide up to 15X speedup over baseline models and present a flight demonstration video of MR-iFLY's vision-based collision avoidance technology. We argue that these empirical results substantiate MR-iFLY as a candidate for use in reducing communication overhead between nodes in 6G communication swarms by providing standalone collision avoidance and navigation capabilities.

show abstract

“…Describing a global proposal, based on MIL, that demonstrates a high generalization capability for anomaly detection in unseen real scenarios in the Wild, understanding "in the Wild" as in non-prepared daily scenarios, instead of in lab-based ones [3,4].…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild

Sarker

Losada

Marrón

et al. 2021

Sensors

View full text Add to dashboard Cite

Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.

show abstract

Real-Time Single Image Depth Perception in the Wild with Handheld Devices

Cited by 44 publications

References 43 publications

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

Machine Learning Subsystem for Autonomous Collision Avoidance on a small UAS with Embedded GPU

Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild

Contact Info

Product

Resources

About