Object detection using YOLO: challenges, architectural successors, datasets and applications

Abstract

Object detection is one of the predominant and challenging problems in computer vision. Over the decade, with the expeditious evolution of deep learning, researchers have extensively experimented and contributed in the performance enhancement of object detection and related tasks such as object classification, localization, and segmentation using underlying deep models. Broadly, object detectors are classified into two categories viz. two stage and single stage object detectors. Two stage detectors mainly focus on selective region proposals strategy via complex architecture; however, single stage detectors focus on all the spatial region proposals for the possible detection of objects via relatively simpler architecture in one shot. Performance of any object detector is evaluated through detection accuracy and inference time. Generally, the detection accuracy of two stage detectors outperforms single stage object detectors. However, the inference time of single stage detectors is better compared to its counterparts. Moreover, with the advent of YOLO (You Only Look Once) and its architectural successors, the detection accuracy is improving significantly and sometime it is better than two stage detectors. YOLOs are adopted in various applications majorly due to their faster inferences rather than considering detection accuracy. As an example, detection accuracies are 63.4 and 70 for YOLO and Fast-RCNN respectively, however, inference time is around 300 times faster in case of YOLO. In this paper, we present a comprehensive review of single stage object detectors specially YOLOs, regression formulation, their architecture advancements, and performance statistics. Moreover, we summarize the comparative illustration between two stage and single stage object detectors, among different versions of YOLOs, applications based on two stage detectors, and different versions of YOLOs along with the future research directions.

Keywords: Computer vision; Convolutional neural networks; Deep learning; Object detection; YOLO.

Fig. 1

Classification, Localization, and Segmentation in Single and Multiple Objects image [13]

Fig. 2

Generic architecture of single stage object detectors [29]

Fig. 3

Year wise evolution of object detection algorithms

Fig. 4

Organization of the Review

Fig. 5

Two stage object detectors (a) RCNN (b) Fast-RCNN (c) Faster-RCNN [44]

Fig. 6

Generic architecture of Convolutional neural networks [2]

Fig. 7

Convolutional Neural Network Layered Operations (http://cs231n.github.io/convolutional-networks/). a Conv-layer b Max-pooling layer c ReLU activation

Fig. 8

VGG architecture [50]

Fig. 9

Network in Network architecture [39]

Fig. 10

Global Average Pooling [85]

Fig. 11

GoogLeNet architecture [67]

Fig. 12

Inception module of the GoogLeNet architecture [65]

Fig. 13

ResNet architecture demonstrating the skip connections [11]

Fig. 14

Dividing the image into grid cells and predictions corresponding to one grid cell

Fig. 15

Multiple bounding boxes and their overlapping with the ground truth (a) Multiple bounding boxes (b) high overlapping (c) low overlapping

Fig. 16

The effect of Non-Max Suppression in Object detection using YOLO

Fig. 17

Computational schematic of Intersection over Union (IoU)

Fig. 18

YOLO architecture for object detection and localization [56]

Fig. 19

Layer wise architectural operations in Darknet-19 framework [54]

Fig. 20

Skip connections in the ResNet Module [25]

Fig. 21

Architecture of YOLO (v3) [81]

Fig. 22

CSPNet vs DenseNet architecture utilized in YOLO-v4 [73]. a CSPNet b DenseNet