Object detection is a hot topic with various applications in computer vision, e.g., image understanding, autonomous driving, and video surveillance. Much of the progresses have been driven by the availability of object detection benchmark datasets, including PASCAL VOC, ImageNet, and MS COCO. However, object detection on the drone platform is still a challenging task, due to various factors such as view point change, occlusion, and scales. To narrow the gap between current object detection performance and the real-world requirements, we organized the Vision Meets Drone (VisDrone2018) Object Detection in Image challenge in conjunction with the 15th European Conference on Computer Vision (ECCV 2018). Specifically, we release a large-scale drone-based dataset, including 8, 599 images (6, 471 for training, 548 for validation, and 1, 580 for testing) with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc. Featuring a diverse real-world scenarios, the dataset was collected using various drone models, in different scenarios (across 14 different cities spanned over thousands of kilometres), and under various weather and lighting conditions. We mainly focus on ten object categories in object detection, i.e., pedestrian, person, car, van, bus, truck, motor, bicycle, awning-tricycle, and tricycle. Some rarely occurring special vehicles (e.g., machineshop truck, forklift truck, and tanker) are ignored in evaluation. The dataset is extremely challenging due to various factors, including large scale and pose variations, occlusion, and clutter background. We present the evaluation protocol of the VisDrone-DET2018 challenge and the comparison results of 38 detectors on the released dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/ . We expect the challenge to largely boost the research and development in object detection in images on drone platforms.

Discriminative correlation filter (DCF)-based trackers have recently exhibited high efficiency and impressive robustness to challenging factors, such as illumination change and partial occlusion. However, in cases with fast motion and full occlusion, these trackers drift off soon and can hardly re-detect the target from the restricted search region due to the boundary effect. On the contrary, recent work using a fully convolutional Siamese network (Siamfc) locates the exemplar image within a large search image but suffers from coarse location and distractors. In this paper, we propose a real-time complementary tracker (RCT) by integrating DCF and Siamfc into a two-stage tracking framework where DCF and Siamfc share mutual advantages and complement each other. In the first stage of this framework, RCT locates the target coarsely but robustly with Siamfc. In the second stage, the derived coarse location is refined by DCF for higher accuracy. For efficiency reasons, Siamfc in the first stage is activated occasionally based on the tracking status inferred from the correlation response map of DCF in the second stage. Comprehensive experiments are performed on three popular benchmark datasets: OTB2013, OTB2015, and VOT2016. On OTB2013, RCT runs with over 40 f/s and achieves an absolute gain of 4.8% and 5.2% in mean overlap precision compared with two base trackers (Staple and Siamfc). On VOT2016, RCT makes a good balance between performance and efficiency, ranking fifth in EAO and first in EFO compared with the top five trackers.

A flexible new technique is proposed to calibrate the geometric model of line scan cameras. In this technique, the line scan camera is rigidly coupled to a calibrated frame camera to establish a pair of stereo cameras. The linear displacements and rotation angles between the two cameras are fixed but unknown. This technique only requires the pair of stereo cameras to observe a specially designed planar pattern shown at a few (at least two) different orientations. At each orientation, a stereo pair is obtained including a linear array image and a frame image. Radial distortion of the line scan camera is modeled. The calibration scheme includes two stages. First, point correspondences are established from the pattern geometry and the projective invariance of cross-ratio. Second, with a two-step calibration procedure, the intrinsic parameters of the line scan camera are recovered from several stereo pairs together with the rigid transform parameters between the pair of stereo cameras. Both computer simulation and real data experiments are conducted to test the precision and robustness of the calibration algorithm, and very good calibration results have been obtained. Compared with classical techniques which use three-dimensional calibration objects or controllable moving platforms, our technique is affordable and flexible in close-range photogrammetric applications.

Recently, the performance advancement of discriminative correlation filter (DCF) based trackers is predominantly driven by the use of deep convolutional features. As convolutional features from multiple layers capture different target information, existing works integrate hierarchical convolutional features to enhance target representation. However, these works separate feature integration from DCF learning and hardly benefit from end-to-end training. In this letter, we incorporates feature integration and DCF learning in a unified convolutional neural network. This network reformulates feature integration as a differential module that concatenates features from the shallow and deep layers. A channel attention mechanism is introduced to adaptively impose channel-wise weight on the integrated features. Experimental results on OTB100 and UAV123 demonstrate that our method achieves significant performance improvement while running in real-time.