Estimation of 6D Object Pose Using a 2D Bounding Box

Abstract

This paper provides an efficient way of addressing the problem of detecting or estimating the 6-Dimensional (6D) pose of objects from an RGB image. A quaternion is used to define an object′s three-dimensional pose, but the pose represented by q and the pose represented by -q are equivalent, and the L2 loss between them is very large. Therefore, we define a new quaternion pose loss function to solve this problem. Based on this, we designed a new convolutional neural network named Q-Net to estimate an object’s pose. Considering that the quaternion′s output is a unit vector, a normalization layer is added in Q-Net to hold the output of pose on a four-dimensional unit sphere. We propose a new algorithm, called the Bounding Box Equation, to obtain 3D translation quickly and effectively from 2D bounding boxes. The algorithm uses an entirely new way of assessing the 3D rotation (R) and 3D translation rotation (t) in only one RGB image. This method can upgrade any traditional 2D-box prediction algorithm to a 3D prediction model. We evaluated our model using the LineMod dataset, and experiments have shown that our methodology is more acceptable and efficient in terms of L2 loss and computational time.

Pose Detection of Aerial Image Object Based on Constrained Neural Network

“…We calculate the translation T of the object according to the Bounding Box Equation technology proposed in the reference [19].…”

“…In addition, according to FIGURE 6, it can be seen that the AP value of Plane is the highest and that of CC is the lowest. This is because the number of samples of CC class is too small, and the results correspond to Based on the attitude quaternion of the object, the threedimensional position and attitude of the object relative to the camera can be further obtained by using the method of literature [19]. The experimental effect of DOTA1.5 data set is shown in FIGURE 7.…”

State Estimation of Axisymmetric Target Based on Beacon Linear Features and View Relation

“…Each experiment fixes the total effective frames = 100, under the condition of three kinds of detection diagram, as shown in Figure 8; blue box, blue dot, green line, and red dot represent target detection and its confidence, beacon corner, straight line feature, and center point detection results, respectively. Regarding the description of the rotation state of the target object, there are various methods to describe the rotation state, and the commonly used methods are Euler angles [30] and quaternion [31]. Among them, the quaternion state description method tends to use numbers with certain calculation rules to describe the rotation state of the target object, which can be displayed intuitively through the certain calculation.…”

“…The measurement results expressed by the RPY angle are shown in Tables 2-4, respectively. Regarding the description of the rotation state of the target object, there are various methods to describe the rotation state, and the commonly used methods are Euler angles [30] and quaternion [31]. Among them, the quaternion state description method tends to use numbers with certain calculation rules to describe the rotation state of the target object, which can be displayed intuitively through the certain calculation.…”