Clustered Object Detection in Aerial Images

Abstract

Detecting objects in aerial images is challenging for at least two reasons: (1) target objects like pedestrians are very small in pixels, making them hardly distinguished from surrounding background; and (2) targets are in general sparsely and non-uniformly distributed, making the detection very inefficient. In this paper, we address both issues inspired by observing that these targets are often clustered. In particular, we propose a Clustered Detection (ClusDet) network that unifies object clustering and detection in an end-to-end framework. The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet). Given an input image, CPNet produces object cluster regions and ScaleNet estimates object scales for these regions. Then, each scale-normalized cluster region is fed into DetecNet for object detection. ClusDet has several advantages over previous solutions: (1) it greatly reduces the number of chips for final object detection and hence achieves high running time efficiency, (2) the clusterbased scale estimation is more accurate than previously used single-object based ones, hence effectively improves the detection for small objects, and (3) the final DetecNet is dedicated for clustered regions and implicitly models the prior context information so as to boost detection accuracy. The proposed method is tested on three popular aerial image datasets including VisDrone, UAVDT and DOTA. In all experiments, ClusDet achieves promising performance in comparison with state-of-the-art detectors. Code will be available in https://github.com/fyangneil. * Corresponding author. Aerial Image Cluster-wise EvenlyObject Coverage per Chip (ratio of objects in chip to whole image) Total Chips Sparse Common Clustered Figure 1: Comparison of grid-based uniform partition and the proposed cluster-based partition. For the narrative purpose, we intentionally classify a chip into three types: sparse, common, and clustered. We observe that, for gridbased uniform partition, more than 73% chips are sparse (including 23% chips with zero objects), around 25% chips are common, and about 2% chips are clustered. By contrast, for cluster-based partition, around 50% chips are sparse, 35% are common, and about 15% belong to clustered chips, which is 7× more than that of grid-based partition.images in MS COCO [22]) in recent years. Despite the promising results for general object detection, the performance of these detectors on the aerial images (e.g., 2,000×1,500 pixels in VisDrone [37]) are far from satisfactory in both accuracy and efficiency, which are caused by two challenges: (1) targets typically have small scales relative to the images; and (2) targets are generally sparsely and non-uniformly distributed in the whole image.

Deep Learning Based Wildfire Event Object Detection from 4K Aerial Images Acquired by UAS

“…Alexe [23] proposed a context-driven region search method and Rzicka [24] created an attention pipeline to actively crop the sub-regions within small objects. Recently, Yang [25] extracted sub-regions with a cluster proposed sub-network and used an iterative cluster merging algorithm to merge the sub-regions.…”

Multi-Scale Vehicle Detection in High-Resolution Aerial Images With Context Information

“…We compared our method with other SOTA methods on UAVDT dataset including: R-FCN [18], RON [53], SSD [23], Faster RCNN (FRCNN) [17], ClusDet [54] and DMNet [38]. All experiment results of other SOTA methods are obtained from [38] and the detection performance is illustrated in Table 6.…”

AE-RTISNet: Aeronautics Engine Radiographic Testing Inspection System Net with Improved Fast Region-based Convolutional Neural Networks Framework

“…This chapters and sections detail on image enhancement [11] method that performs an automated multiple defect detection model that is no doubt the best way to applicability of maintenance detection Fast R-CNN algorithm solved original low pixel X-ray films identification problem. Our prepare work, has focused on image enhancement , feature segmentation [12], object classification [13] and multiple detections [14]. Our focus is based on addressing the different type aeronautics engine material hidden crack object classification and detection tasks presented in the following sections.…”