Recent advances in deep learning for object detection

Wu, Xiongwei; Sahoo, Debasish; Hoi, Steven C. H.

doi:10.1016/j.neucom.2020.01.085

Cited by 638 publications

(295 citation statements)

References 273 publications

Supporting

Mentioning

281

Contrasting

Unclassified

Order By: Relevance

“…IoU is a geometrical statistic which measures the area of the intersection divided by the area of overlap of the ground truth bounding box and the predicted bounding box. This indicator is very commonly used for the validation of deep learning object detection models, and an IoU > 0.5 is generally accepted as a proper threshold for a successful detection [21,32,45,46]. An IoU > 0.5 was the threshold to select the bounding boxes that were further statistically processed to assess the detection performance.…”

Section: Detecting With Single Modelsmentioning

confidence: 99%

Individual Tree-Crown Detection and Species Classification in Very High-Resolution Remote Sensing Imagery Using a Deep Learning Ensemble Model

et al. 2020

View full text Add to dashboard Cite

Traditional methods for individual tree-crown (ITC) detection (image classification, segmentation, template matching, etc.) applied to very high-resolution remote sensing imagery have been shown to struggle in disparate landscape types or image resolutions due to scale problems and information complexity. Deep learning promised to overcome these shortcomings due to its superior performance and versatility, proven with reported detection rates of ~90%. However, such models still find their limits in transferability across study areas, because of different tree conditions (e.g., isolated trees vs. compact forests) and/or resolutions of the input data. This study introduces a highly replicable deep learning ensemble design for ITC detection and species classification based on the established single shot detector (SSD) model. The ensemble model design is based on varying the input data for the SSD models, coupled with a voting strategy for the output predictions. Very high-resolution unmanned aerial vehicles (UAV), aerial remote sensing imagery and elevation data are used in different combinations to test the performance of the ensemble models in three study sites with highly contrasting spatial patterns. The results show that ensemble models perform better than any single SSD model, regardless of the local tree conditions or image resolution. The detection performance and the accuracy rates improved by 3–18% with only as few as two participant single models, regardless of the study site. However, when more than two models were included, the performance of the ensemble models only improved slightly and even dropped.

show abstract

Section: Detecting With Single Modelsmentioning

confidence: 99%

Individual Tree-Crown Detection and Species Classification in Very High-Resolution Remote Sensing Imagery Using a Deep Learning Ensemble Model

et al. 2020

View full text Add to dashboard Cite

show abstract

“…When picking the ODCNNs we wanted to find the best trade-off between execution time and mean average precision. In literature, there exist several surveys [36][37][6] on object detection, however, all of them focus on the mAP metric. Eventually, we picked three kinds of NNs that are designed to run in real-time, are well-established in literature and lead to the best results 5 .…”

Section: Neural Networkmentioning

confidence: 99%

A Systematic Assessment of Embedded Neural Networks for Object Detection

Verucchi

Brilli

Sapienza

et al. 2020

2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)

View full text Add to dashboard Cite

Object detection is arguably one of the most important and complex tasks to enable the advent of next-generation autonomous systems. Recent advancements in deep learning techniques allowed a significant improvement in detection accuracy and latency of modern neural networks, allowing their adoption in automotive, avionics and industrial embedded systems, where performances are required to meet size, weight and power constraints. Multiple benchmarks and surveys exist to compare stateof-the-art detection networks, profiling important metrics, like precision, latency and power efficiency on Commercial-off-the-Shelf (COTS) embedded platforms. However, we observed a fundamental lack of fairness in the existing comparisons, with a number of implicit assumptions that may significantly bias the metrics of interest. This includes using heterogeneous settings for the input size, training dataset, threshold confidences, and, most importantly, platform-specific optimizations, that are especially important when assessing latency and energy-related values. The lack of uniform comparisons is mainly due to the significant effort required to re-implement network models, whenever openly available, on the specific platforms, to properly configure the available acceleration engines for optimizing performance, and to retrain the model using a homogeneous dataset. This paper aims at filling this gap, providing a comprehensive and fair comparison of the best-in-class Convolution Neural Networks (CNNs) for real-time embedded systems, detailing the effort made to achieve an unbiased characterization on cutting-edge system-on-chips. Multi-dimensional trade-offs are explored for achieving a proper configuration of the available programmable accelerators for neural inference, adopting the best available software libraries. To stimulate the adoption of fair benchmarking assessments, the framework is released to the public in an open source repository.

show abstract

“…CenterNet [37] is a one-stage detector, anchor-free method. Reference [37] proposed a new center-based framework based on a single Hourglass network without FPN structure [38]. The object is represented by the central point of the bounding box.…”

Section: Centernetmentioning

confidence: 99%

Detecting Objects from Space: An Evaluation of Deep-Learning Modern Approaches

et al. 2020

View full text Add to dashboard Cite

Unmanned aircraft systems or drones enable us to record or capture many scenes from the bird’s-eye view and they have been fast deployed to a wide range of practical domains, i.e., agriculture, aerial photography, fast delivery and surveillance. Object detection task is one of the core steps in understanding videos collected from the drones. However, this task is very challenging due to the unconstrained viewpoints and low resolution of captured videos. While deep-learning modern object detectors have recently achieved great success in general benchmarks, i.e., PASCAL-VOC and MS-COCO, the robustness of these detectors on aerial images captured by drones is not well studied. In this paper, we present an evaluation of state-of-the-art deep-learning detectors including Faster R-CNN (Faster Regional CNN), RFCN (Region-based Fully Convolutional Networks), SNIPER (Scale Normalization for Image Pyramids with Efficient Resampling), Single-Shot Detector (SSD), YOLO (You Only Look Once), RetinaNet, and CenterNet for the object detection in videos captured by drones. We conduct experiments on VisDrone2019 dataset which contains 96 videos with 39,988 annotated frames and provide insights into efficient object detectors for aerial images.

show abstract

Recent advances in deep learning for object detection

Cited by 638 publications

References 273 publications

Individual Tree-Crown Detection and Species Classification in Very High-Resolution Remote Sensing Imagery Using a Deep Learning Ensemble Model

Individual Tree-Crown Detection and Species Classification in Very High-Resolution Remote Sensing Imagery Using a Deep Learning Ensemble Model

A Systematic Assessment of Embedded Neural Networks for Object Detection

Detecting Objects from Space: An Evaluation of Deep-Learning Modern Approaches

Contact Info

Product

Resources

About